{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/task/text-generation/papers/2","list_of":"/task/text-generation","task":"Text Generation","archive":{"snapshot":"2025-07-28"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"archive","order_definition":"repositories listed in the archive (most first), then date (newest first), then slug","page":2,"pages_in_order":54,"rows_per_page":100,"rows":[101,200],"of":5335,"counts":{"archive_papers_tagged":5335,"with_a_code_link":2047,"where_syntology_ran_a_sample":610,"not_listed_spam_title":0,"listed":5335,"listed_where_code_ran":610,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":503,"every_run_a_failure_of_syntologys_instrument":107,"listed_with_a_run_with_no_instrument_failure":503,"listed_every_run_a_failure_of_syntologys_instrument":107,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"first_page":"/task/text-generation","prev":"/task/text-generation","next":"/task/text-generation/papers/3","papers":[{"url":"/paper/latent-space-secrets-of-denoising-text","slug":"latent-space-secrets-of-denoising-text","title":"Educating Text Autoencoders: Latent Representation Guidance via Denoising","date":"2019-05-29","arxiv_id":"1905.12777","repositories_listed":3,"syntology":null},{"url":"/paper/jointly-measuring-diversity-and-quality-in","slug":"jointly-measuring-diversity-and-quality-in","title":"Jointly Measuring Diversity and Quality in Text Generation Models","date":"2019-04-08","arxiv_id":"1904.03971","repositories_listed":3,"syntology":{"n":6,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":1,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/jointly-measuring-diversity-and-quality-in#ran","syntology_url":"https://syntology.ai/paper/1904.03971","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1904.03971"}},"official":{"repos":["IAmS4n/TextGenerationEvaluationMetrics"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/text-generation-from-knowledge-graphs-with","slug":"text-generation-from-knowledge-graphs-with","title":"Text Generation from Knowledge Graphs with Graph Transformers","date":"2019-04-04","arxiv_id":"1904.02342","repositories_listed":3,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/text-generation-from-knowledge-graphs-with#ran","syntology_url":"https://syntology.ai/paper/1904.02342","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1904.02342"}},"official":{"repos":["rikdz/GraphWriter"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/toward-diverse-text-generation-with-inverse","slug":"toward-diverse-text-generation-with-inverse","title":"Toward Diverse Text Generation with Inverse Reinforcement Learning","date":"2018-04-30","arxiv_id":"1804.11258","repositories_listed":3,"syntology":null},{"url":"/paper/dp-gan-diversity-promoting-generative","slug":"dp-gan-diversity-promoting-generative","title":"DP-GAN: Diversity-Promoting Generative Adversarial Network for Generating Informative and Diversified Text","date":"2018-02-05","arxiv_id":"1802.01345","repositories_listed":3,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/dp-gan-diversity-promoting-generative#ran","syntology_url":"https://syntology.ai/paper/1802.01345","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1802.01345"}},"official":{"repos":["lancopku/DPGAN"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/table-to-text-generation-by-structure-aware","slug":"table-to-text-generation-by-structure-aware","title":"Table-to-text Generation by Structure-aware Seq2seq Learning","date":"2017-11-27","arxiv_id":"1711.09724","repositories_listed":3,"syntology":null},{"url":"/paper/relevance-of-unsupervised-metrics-in-task","slug":"relevance-of-unsupervised-metrics-in-task","title":"Relevance of Unsupervised Metrics in Task-Oriented Dialogue for Evaluating Natural Language Generation","date":"2017-06-29","arxiv_id":"1706.09799","repositories_listed":3,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/relevance-of-unsupervised-metrics-in-task#ran","syntology_url":"https://syntology.ai/paper/1706.09799","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1706.09799"}},"official":{"repos":["Maluuba/nlg-eval"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/language-generation-with-recurrent-generative","slug":"language-generation-with-recurrent-generative","title":"Language Generation with Recurrent Generative Adversarial Networks without Pre-training","date":"2017-06-05","arxiv_id":"1706.01399","repositories_listed":3,"syntology":null},{"url":"/paper/improved-variational-autoencoders-for-text","slug":"improved-variational-autoencoders-for-text","title":"Improved Variational Autoencoders for Text Modeling using Dilated Convolutions","date":"2017-02-27","arxiv_id":"1702.08139","repositories_listed":3,"syntology":null},{"url":"/paper/a-hybrid-convolutional-variational","slug":"a-hybrid-convolutional-variational","title":"A Hybrid Convolutional Variational Autoencoder for Text Generation","date":"2017-02-08","arxiv_id":"1702.02390","repositories_listed":3,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/a-hybrid-convolutional-variational#ran","syntology_url":"https://syntology.ai/paper/1702.02390","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1702.02390"}},"official":{"repos":["stas-semeniuta/textvae"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/an-actor-critic-algorithm-for-sequence","slug":"an-actor-critic-algorithm-for-sequence","title":"An Actor-Critic Algorithm for Sequence Prediction","date":"2016-07-24","arxiv_id":"1607.07086","repositories_listed":3,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 1 unverified","sample_list":"/paper/an-actor-critic-algorithm-for-sequence#ran","syntology_url":"https://syntology.ai/paper/1607.07086","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1607.07086"}},"official":{"repos":["rizar/actor-critic-public"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"url":"/paper/hypoeval-hypothesis-guided-evaluation-for","slug":"hypoeval-hypothesis-guided-evaluation-for","title":"HypoEval: Hypothesis-Guided Evaluation for Natural Language Generation","date":"2025-04-09","arxiv_id":"2504.07174","repositories_listed":2,"syntology":null},{"url":"/paper/beyond-factual-accuracy-evaluating-coverage","slug":"beyond-factual-accuracy-evaluating-coverage","title":"Beyond Factual Accuracy: Evaluating Coverage of Diverse Factual Information in Long-form Text Generation","date":"2025-01-07","arxiv_id":"2501.03545","repositories_listed":2,"syntology":null},{"url":"/paper/ecg-byte-a-tokenizer-for-end-to-end","slug":"ecg-byte-a-tokenizer-for-end-to-end","title":"ECG-Byte: A Tokenizer for End-to-End Generative Electrocardiogram Language Modeling","date":"2024-12-18","arxiv_id":"2412.14373","repositories_listed":2,"syntology":null},{"url":"/paper/ad-llm-benchmarking-large-language-models-for","slug":"ad-llm-benchmarking-large-language-models-for","title":"AD-LLM: Benchmarking Large Language Models for Anomaly Detection","date":"2024-12-15","arxiv_id":"2412.11142","repositories_listed":2,"syntology":{"n":7,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/ad-llm-benchmarking-large-language-models-for#ran","syntology_url":"https://syntology.ai/paper/2412.11142","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.11142"}},"official":{"repos":["usc-fortis/ad-llm"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/exact-aggregation-for-federated-and-efficient","slug":"exact-aggregation-for-federated-and-efficient","title":"FedEx-LoRA: Exact Aggregation for Federated and Efficient Fine-Tuning of Foundation Models","date":"2024-10-12","arxiv_id":"2410.09432","repositories_listed":2,"syntology":null},{"url":"/paper/one-initialization-to-rule-them-all-fine","slug":"one-initialization-to-rule-them-all-fine","title":"Parameter Efficient Fine-tuning via Explained Variance Adaptation","date":"2024-10-09","arxiv_id":"2410.07170","repositories_listed":2,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":1,"n_no_contract":1,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 1 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/one-initialization-to-rule-them-all-fine#ran","syntology_url":"https://syntology.ai/paper/2410.07170","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.07170"}},"official":{"repos":["BenediktAlkin/vtab1k-pytorch","ml-jku/EVA"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/enhancing-high-order-interaction-awareness-in","slug":"enhancing-high-order-interaction-awareness-in","title":"Enhancing High-order Interaction Awareness in LLM-based Recommender Model","date":"2024-09-30","arxiv_id":"2409.19979","repositories_listed":2,"syntology":null},{"url":"/paper/spinning-the-golden-thread-benchmarking-long","slug":"spinning-the-golden-thread-benchmarking-long","title":"LongGenBench: Benchmarking Long-Form Generation in Long Context LLMs","date":"2024-09-03","arxiv_id":"2409.02076","repositories_listed":2,"syntology":{"n":8,"n_ran":8,"n_constructed":0,"n_ran_checked":7,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":8,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/spinning-the-golden-thread-benchmarking-long#ran","syntology_url":"https://syntology.ai/paper/2409.02076","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.02076"}},"official":{"repos":["mozhu621/SGT","mozhu621/longgenbench"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/fairer-preferences-elicit-improved-human","slug":"fairer-preferences-elicit-improved-human","title":"Fairer Preferences Elicit Improved Human-Aligned Large Language Model Judgments","date":"2024-06-17","arxiv_id":"2406.11370","repositories_listed":2,"syntology":{"n":29,"n_ran":20,"n_constructed":4,"n_ran_checked":10,"n_instrument":10,"n_unverified":9,"n_honours":3,"n_violates":2,"n_no_contract":5,"n_pointer_only":2,"phrase":"20 ran (of which 4 constructed an object rather than computing a result; 10 with no instrument failure: 3 honoured, 2 violated, 5 with no contract checked; 10 where Syntology's instrument failed) · 9 unverified","sample_list":"/paper/fairer-preferences-elicit-improved-human#ran","syntology_url":"https://syntology.ai/paper/2406.11370","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.11370"}},"official":{"repos":["cambridgeltl/zepo"],"state":"official (archive's flag): 17 ran","n_ran":17,"n_constructed":3,"n_ran_no_instrument_failure":7,"n_unverified":6,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/in-context-editing-learning-knowledge-from","slug":"in-context-editing-learning-knowledge-from","title":"In-Context Editing: Learning Knowledge from Self-Induced Distributions","date":"2024-06-17","arxiv_id":"2406.11194","repositories_listed":2,"syntology":{"n":8,"n_ran":6,"n_constructed":0,"n_ran_checked":3,"n_instrument":3,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":8,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/in-context-editing-learning-knowledge-from#ran","syntology_url":"https://syntology.ai/paper/2406.11194","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.11194"}},"official":{"repos":["bigai-ai/ICE"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/regularizing-hidden-states-enables-learning","slug":"regularizing-hidden-states-enables-learning","title":"Regularizing Hidden States Enables Learning Generalizable Reward Model for LLMs","date":"2024-06-14","arxiv_id":"2406.10216","repositories_listed":2,"syntology":{"n":7,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/regularizing-hidden-states-enables-learning#ran","syntology_url":"https://syntology.ai/paper/2406.10216","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.10216"}},"official":{"repos":["yangrui2015/generalizable-reward-model"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/cudrt-benchmarking-the-detection-of-human-vs","slug":"cudrt-benchmarking-the-detection-of-human-vs","title":"Towards Reliable Detection of LLM-Generated Texts: A Comprehensive Evaluation Framework with CUDRT","date":"2024-06-13","arxiv_id":"2406.09056","repositories_listed":2,"syntology":null},{"url":"/paper/are-you-still-on-track-catching-llm-task","slug":"are-you-still-on-track-catching-llm-task","title":"Get my drift? Catching LLM Task Drift with Activation Deltas","date":"2024-06-02","arxiv_id":"2406.00799","repositories_listed":2,"syntology":{"n":5,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/are-you-still-on-track-catching-llm-task#ran","syntology_url":"https://syntology.ai/paper/2406.00799","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.00799"}},"official":{"repos":["microsoft/TaskTracker"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/kernel-language-entropy-fine-grained","slug":"kernel-language-entropy-fine-grained","title":"Kernel Language Entropy: Fine-grained Uncertainty Quantification for LLMs from Semantic Similarities","date":"2024-05-30","arxiv_id":"2405.20003","repositories_listed":2,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/kernel-language-entropy-fine-grained#ran","syntology_url":"https://syntology.ai/paper/2405.20003","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.20003"}},"official":{"repos":["alexandervnikitin/kernel-language-entropy"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/benchmarking-large-language-models-on-cflue-a","slug":"benchmarking-large-language-models-on-cflue-a","title":"Benchmarking Large Language Models on CFLUE -- A Chinese Financial Language Understanding Evaluation Dataset","date":"2024-05-17","arxiv_id":"2405.10542","repositories_listed":2,"syntology":null},{"url":"/paper/semantic-routing-for-enhanced-performance-of","slug":"semantic-routing-for-enhanced-performance-of","title":"Semantic Routing for Enhanced Performance of LLM-Assisted Intent-Based 5G Core Network Management and Orchestration","date":"2024-04-24","arxiv_id":"2404.15869","repositories_listed":2,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/semantic-routing-for-enhanced-performance-of#ran","syntology_url":"https://syntology.ai/paper/2404.15869","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.15869"}},"official":null}},{"url":"/paper/llm-attributor-interactive-visual-attribution","slug":"llm-attributor-interactive-visual-attribution","title":"LLM Attributor: Interactive Visual Attribution for LLM Generation","date":"2024-04-01","arxiv_id":"2404.01361","repositories_listed":2,"syntology":null},{"url":"/paper/urbanvlp-a-multi-granularity-vision-language","slug":"urbanvlp-a-multi-granularity-vision-language","title":"UrbanVLP: Multi-Granularity Vision-Language Pretraining for Urban Socioeconomic Indicator Prediction","date":"2024-03-25","arxiv_id":"2403.16831","repositories_listed":2,"syntology":{"n":20,"n_ran":15,"n_constructed":0,"n_ran_checked":12,"n_instrument":3,"n_unverified":5,"n_honours":1,"n_violates":3,"n_no_contract":8,"n_pointer_only":20,"phrase":"15 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 1 honoured, 3 violated, 8 with no contract checked; 3 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/urbanvlp-a-multi-granularity-vision-language#ran","syntology_url":"https://syntology.ai/paper/2403.16831","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.16831"}},"official":{"repos":["citymind-lab/urbanvlp"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":5,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/embedded-named-entity-recognition-using","slug":"embedded-named-entity-recognition-using","title":"Embedded Named Entity Recognition using Probing Classifiers","date":"2024-03-18","arxiv_id":"2403.11747","repositories_listed":2,"syntology":{"n":5,"n_ran":4,"n_constructed":2,"n_ran_checked":4,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":5,"phrase":"4 ran (of which 2 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/embedded-named-entity-recognition-using#ran","syntology_url":"https://syntology.ai/paper/2403.11747","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.11747"}},"official":{"repos":["nicpopovic/stoke","nicpopovic/ember"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":2,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/evaluating-named-entity-recognition","slug":"evaluating-named-entity-recognition","title":"Evaluating Named Entity Recognition: A comparative analysis of mono- and multilingual transformer models on a novel Brazilian corporate earnings call transcripts dataset","date":"2024-03-18","arxiv_id":"2403.12212","repositories_listed":2,"syntology":null},{"url":"/paper/dsp-dynamic-sequence-parallelism-for-multi","slug":"dsp-dynamic-sequence-parallelism-for-multi","title":"DSP: Dynamic Sequence Parallelism for Multi-Dimensional Transformers","date":"2024-03-15","arxiv_id":"2403.10266","repositories_listed":2,"syntology":{"n":19,"n_ran":13,"n_constructed":0,"n_ran_checked":11,"n_instrument":2,"n_unverified":6,"n_honours":1,"n_violates":1,"n_no_contract":9,"n_pointer_only":0,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 1 honoured, 1 violated, 9 with no contract checked; 2 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/dsp-dynamic-sequence-parallelism-for-multi#ran","syntology_url":"https://syntology.ai/paper/2403.10266","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.10266"}},"official":{"repos":["nus-hpc-ai-lab/opendit"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/generative-pretrained-structured-transformers","slug":"generative-pretrained-structured-transformers","title":"Generative Pretrained Structured Transformers: Unsupervised Syntactic Language Models at Scale","date":"2024-03-13","arxiv_id":"2403.08293","repositories_listed":2,"syntology":{"n":7,"n_ran":4,"n_constructed":2,"n_ran_checked":3,"n_instrument":1,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"4 ran (of which 2 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/generative-pretrained-structured-transformers#ran","syntology_url":"https://syntology.ai/paper/2403.08293","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.08293"}},"official":{"repos":["ant-research/structuredlm_rtdt"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/triples-to-isixhosa-t2x-addressing-the","slug":"triples-to-isixhosa-t2x-addressing-the","title":"Triples-to-isiXhosa (T2X): Addressing the Challenges of Low-Resource Agglutinative Data-to-Text Generation","date":"2024-03-12","arxiv_id":"2403.07567","repositories_listed":2,"syntology":null},{"url":"/paper/defending-against-unforeseen-failure-modes","slug":"defending-against-unforeseen-failure-modes","title":"Defending Against Unforeseen Failure Modes with Latent Adversarial Training","date":"2024-03-08","arxiv_id":"2403.05030","repositories_listed":2,"syntology":null},{"url":"/paper/halc-object-hallucination-reduction-via","slug":"halc-object-hallucination-reduction-via","title":"HALC: Object Hallucination Reduction via Adaptive Focal-Contrast Decoding","date":"2024-03-01","arxiv_id":"2403.00425","repositories_listed":2,"syntology":{"n":12,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/halc-object-hallucination-reduction-via#ran","syntology_url":"https://syntology.ai/paper/2403.00425","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.00425"}},"official":{"repos":["billchan226/halc","bradyfu/awesome-multimodal-large-language-models"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/seeing-is-believing-mitigating-hallucination","slug":"seeing-is-believing-mitigating-hallucination","title":"Seeing is Believing: Mitigating Hallucination in Large Vision-Language Models via CLIP-Guided Decoding","date":"2024-02-23","arxiv_id":"2402.15300","repositories_listed":2,"syntology":{"n":17,"n_ran":11,"n_constructed":0,"n_ran_checked":11,"n_instrument":0,"n_unverified":6,"n_honours":0,"n_violates":0,"n_no_contract":11,"n_pointer_only":17,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 0 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/seeing-is-believing-mitigating-hallucination#ran","syntology_url":"https://syntology.ai/paper/2402.15300","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.15300"}},"official":{"repos":["d-ailin/clip-guided-decoding"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":6,"ran_from_kinds":["official"]}}},{"url":"/paper/the-finben-an-holistic-financial-benchmark","slug":"the-finben-an-holistic-financial-benchmark","title":"FinBen: A Holistic Financial Benchmark for Large Language Models","date":"2024-02-20","arxiv_id":"2402.12659","repositories_listed":2,"syntology":{"n":12,"n_ran":8,"n_constructed":0,"n_ran_checked":6,"n_instrument":2,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":7,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 2 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/the-finben-an-holistic-financial-benchmark#ran","syntology_url":"https://syntology.ai/paper/2402.12659","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.12659"}},"official":{"repos":["the-finai/pixiu"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/k-semstamp-a-clustering-based-semantic","slug":"k-semstamp-a-clustering-based-semantic","title":"k-SemStamp: A Clustering-Based Semantic Watermark for Detection of Machine-Generated Text","date":"2024-02-17","arxiv_id":"2402.11399","repositories_listed":2,"syntology":{"n":9,"n_ran":9,"n_constructed":0,"n_ran_checked":9,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":9,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/k-semstamp-a-clustering-based-semantic#ran","syntology_url":"https://syntology.ai/paper/2402.11399","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.11399"}},"official":{"repos":["bohanhou14/semstamp"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/weblinx-real-world-website-navigation-with","slug":"weblinx-real-world-website-navigation-with","title":"WebLINX: Real-World Website Navigation with Multi-Turn Dialogue","date":"2024-02-08","arxiv_id":"2402.05930","repositories_listed":2,"syntology":{"n":27,"n_ran":21,"n_constructed":0,"n_ran_checked":20,"n_instrument":1,"n_unverified":6,"n_honours":0,"n_violates":1,"n_no_contract":19,"n_pointer_only":0,"phrase":"21 ran (of which 0 constructed an object rather than computing a result; 20 with no instrument failure: 0 honoured, 1 violated, 19 with no contract checked; 1 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/weblinx-real-world-website-navigation-with#ran","syntology_url":"https://syntology.ai/paper/2402.05930","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.05930"}},"official":{"repos":["McGill-NLP/weblinx","McGill-NLP/webllama"],"state":"official (archive's flag): 21 ran","n_ran":21,"n_constructed":0,"n_ran_no_instrument_failure":20,"n_unverified":6,"ran_from_kinds":["official"]}}},{"url":"/paper/linear-time-minimum-bayes-risk-decoding-with","slug":"linear-time-minimum-bayes-risk-decoding-with","title":"Linear-time Minimum Bayes Risk Decoding with Reference Aggregation","date":"2024-02-06","arxiv_id":"2402.04251","repositories_listed":2,"syntology":null},{"url":"/paper/teenytinyllama-open-source-tiny-language","slug":"teenytinyllama-open-source-tiny-language","title":"TeenyTinyLlama: open-source tiny language models trained in Brazilian Portuguese","date":"2024-01-30","arxiv_id":"2401.16640","repositories_listed":2,"syntology":null},{"url":"/paper/code-generation-with-alphacodium-from-prompt","slug":"code-generation-with-alphacodium-from-prompt","title":"Code Generation with AlphaCodium: From Prompt Engineering to Flow Engineering","date":"2024-01-16","arxiv_id":"2401.08500","repositories_listed":2,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/code-generation-with-alphacodium-from-prompt#ran","syntology_url":"https://syntology.ai/paper/2401.08500","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.08500"}},"official":{"repos":["codium-ai/alphacodium"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/authorship-obfuscation-in-multilingual","slug":"authorship-obfuscation-in-multilingual","title":"Authorship Obfuscation in Multilingual Machine-Generated Text Detection","date":"2024-01-15","arxiv_id":"2401.07867","repositories_listed":2,"syntology":null},{"url":"/paper/sh2-self-highlighted-hesitation-helps-you","slug":"sh2-self-highlighted-hesitation-helps-you","title":"SH2: Self-Highlighted Hesitation Helps You Decode More Truthfully","date":"2024-01-11","arxiv_id":"2401.05930","repositories_listed":2,"syntology":{"n":13,"n_ran":6,"n_constructed":0,"n_ran_checked":5,"n_instrument":1,"n_unverified":7,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":13,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 7 unverified","sample_list":"/paper/sh2-self-highlighted-hesitation-helps-you#ran","syntology_url":"https://syntology.ai/paper/2401.05930","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.05930"}},"official":{"repos":["0-kaikai-0/sh2","LUMIA-Group/SH2"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":7,"ran_from_kinds":["official"]}}},{"url":"/paper/e4srec-an-elegant-effective-efficient","slug":"e4srec-an-elegant-effective-efficient","title":"E4SRec: An Elegant Effective Efficient Extensible Solution of Large Language Models for Sequential Recommendation","date":"2023-12-05","arxiv_id":"2312.02443","repositories_listed":2,"syntology":{"n":6,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/e4srec-an-elegant-effective-efficient#ran","syntology_url":"https://syntology.ai/paper/2312.02443","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.02443"}},"official":{"repos":["hestiasky/e4srec"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/data-generation-for-post-ocr-correction-of","slug":"data-generation-for-post-ocr-correction-of","title":"Data Generation for Post-OCR correction of Cyrillic handwriting","date":"2023-11-27","arxiv_id":"2311.15896","repositories_listed":2,"syntology":null},{"url":"/paper/data-to-text-bilingual-generation","slug":"data-to-text-bilingual-generation","title":"Data-to-Text Bilingual Generation","date":"2023-11-24","arxiv_id":"2311.14808","repositories_listed":2,"syntology":null},{"url":"/paper/enhancing-medical-text-evaluation-with-gpt-4","slug":"enhancing-medical-text-evaluation-with-gpt-4","title":"DocLens: Multi-aspect Fine-grained Evaluation for Medical Text Generation","date":"2023-11-16","arxiv_id":"2311.09581","repositories_listed":2,"syntology":null},{"url":"/paper/semqa-semi-extractive-multi-source-question","slug":"semqa-semi-extractive-multi-source-question","title":"SEMQA: Semi-Extractive Multi-Source Question Answering","date":"2023-11-08","arxiv_id":"2311.04886","repositories_listed":2,"syntology":null},{"url":"/paper/automatic-unit-test-data-generation-and-actor","slug":"automatic-unit-test-data-generation-and-actor","title":"Automatic Unit Test Data Generation and Actor-Critic Reinforcement Learning for Code Synthesis","date":"2023-10-20","arxiv_id":"2310.13669","repositories_listed":2,"syntology":null},{"url":"/paper/reward-augmented-decoding-efficient","slug":"reward-augmented-decoding-efficient","title":"Reward-Augmented Decoding: Efficient Controlled Text Generation With a Unidirectional Reward Model","date":"2023-10-14","arxiv_id":"2310.09520","repositories_listed":2,"syntology":{"n":3,"n_ran":2,"n_constructed":2,"n_ran_checked":2,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":3,"phrase":"2 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified; every one of the 2 samples that ran constructed an object rather than computing a result","sample_list":"/paper/reward-augmented-decoding-efficient#ran","syntology_url":"https://syntology.ai/paper/2310.09520","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.09520"}},"official":{"repos":["haikangdeng/RAD"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/semstamp-a-semantic-watermark-with","slug":"semstamp-a-semantic-watermark-with","title":"SemStamp: A Semantic Watermark with Paraphrastic Robustness for Text Generation","date":"2023-10-06","arxiv_id":"2310.03991","repositories_listed":2,"syntology":null},{"url":"/paper/label-supervised-llama-finetuning","slug":"label-supervised-llama-finetuning","title":"Label Supervised LLaMA Finetuning","date":"2023-10-02","arxiv_id":"2310.01208","repositories_listed":2,"syntology":null},{"url":"/paper/controllable-text-generation-with-residual","slug":"controllable-text-generation-with-residual","title":"Controllable Text Generation with Residual Memory Transformer","date":"2023-09-28","arxiv_id":"2309.16231","repositories_listed":2,"syntology":null},{"url":"/paper/efficient-post-training-quantization-with-fp8","slug":"efficient-post-training-quantization-with-fp8","title":"Efficient Post-training Quantization with FP8 Formats","date":"2023-09-26","arxiv_id":"2309.14592","repositories_listed":2,"syntology":null},{"url":"/paper/imagebind-llm-multi-modality-instruction","slug":"imagebind-llm-multi-modality-instruction","title":"ImageBind-LLM: Multi-modality Instruction Tuning","date":"2023-09-07","arxiv_id":"2309.03905","repositories_listed":2,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"0 ran · 1 unverified","sample_list":"/paper/imagebind-llm-multi-modality-instruction#ran","syntology_url":"https://syntology.ai/paper/2309.03905","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.03905"}},"official":{"repos":["opengvlab/llama-adapter"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"url":"/paper/a-methodology-for-generative-spelling","slug":"a-methodology-for-generative-spelling","title":"A Methodology for Generative Spelling Correction via Natural Spelling Errors Emulation across Multiple Domains and Languages","date":"2023-08-18","arxiv_id":"2308.09435","repositories_listed":2,"syntology":null},{"url":"/paper/red-teaming-large-language-models-using-chain","slug":"red-teaming-large-language-models-using-chain","title":"Red-Teaming Large Language Models using Chain of Utterances for Safety-Alignment","date":"2023-08-18","arxiv_id":"2308.09662","repositories_listed":2,"syntology":null},{"url":"/paper/uni-nlx-unifying-textual-explanations-for","slug":"uni-nlx-unifying-textual-explanations-for","title":"Uni-NLX: Unifying Textual Explanations for Vision and Vision-Language Tasks","date":"2023-08-17","arxiv_id":"2308.09033","repositories_listed":2,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":5,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":6,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/uni-nlx-unifying-textual-explanations-for#ran","syntology_url":"https://syntology.ai/paper/2308.09033","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.09033"}},"official":{"repos":["fawazsammani/uni-nlx","fawazsammani/nlxgpt"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/attention-is-not-all-you-need-anymore","slug":"attention-is-not-all-you-need-anymore","title":"Attention Is Not All You Need Anymore","date":"2023-08-15","arxiv_id":"2308.07661","repositories_listed":2,"syntology":null},{"url":"/paper/zyn-zero-shot-reward-models-with-yes-no","slug":"zyn-zero-shot-reward-models-with-yes-no","title":"ZYN: Zero-Shot Reward Models with Yes-No Questions for RLAIF","date":"2023-08-11","arxiv_id":"2308.06385","repositories_listed":2,"syntology":{"n":2,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 2 unverified","sample_list":"/paper/zyn-zero-shot-reward-models-with-yes-no#ran","syntology_url":"https://syntology.ai/paper/2308.06385","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.06385"}},"official":{"repos":["anon23423589675234/zero-shot-reward-models","vicgalle/zero-shot-reward-models"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":[]}}},{"url":"/paper/evaluating-the-generation-capabilities-of","slug":"evaluating-the-generation-capabilities-of","title":"Evaluating the Generation Capabilities of Large Chinese Language Models","date":"2023-08-09","arxiv_id":"2308.04823","repositories_listed":2,"syntology":null},{"url":"/paper/lisa-reasoning-segmentation-via-large","slug":"lisa-reasoning-segmentation-via-large","title":"LISA: Reasoning Segmentation via Large Language Model","date":"2023-08-01","arxiv_id":"2308.00692","repositories_listed":2,"syntology":null},{"url":"/paper/this-is-not-correct-negation-aware-evaluation","slug":"this-is-not-correct-negation-aware-evaluation","title":"This is not correct! Negation-aware Evaluation of Language Generation Systems","date":"2023-07-26","arxiv_id":"2307.13989","repositories_listed":2,"syntology":null},{"url":"/paper/a-systematic-survey-of-prompt-engineering-on","slug":"a-systematic-survey-of-prompt-engineering-on","title":"A Systematic Survey of Prompt Engineering on Vision-Language Foundation Models","date":"2023-07-24","arxiv_id":"2307.12980","repositories_listed":2,"syntology":null},{"url":"/paper/is-chatgpt-involved-in-texts-measure-the","slug":"is-chatgpt-involved-in-texts-measure-the","title":"Is ChatGPT Involved in Texts? Measure the Polish Ratio to Detect ChatGPT-Generated Text","date":"2023-07-21","arxiv_id":"2307.11380","repositories_listed":2,"syntology":null},{"url":"/paper/generative-pretraining-in-multimodality","slug":"generative-pretraining-in-multimodality","title":"Emu: Generative Pretraining in Multimodality","date":"2023-07-11","arxiv_id":"2307.05222","repositories_listed":2,"syntology":{"n":2,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 2 unverified","sample_list":"/paper/generative-pretraining-in-multimodality#ran","syntology_url":"https://syntology.ai/paper/2307.05222","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.05222"}},"official":{"repos":["baaivision/emu"],"state":"official: harvested for another paper","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":[]}}},{"url":"/paper/building-cooperative-embodied-agents","slug":"building-cooperative-embodied-agents","title":"Building Cooperative Embodied Agents Modularly with Large Language Models","date":"2023-07-05","arxiv_id":"2307.02485","repositories_listed":2,"syntology":null},{"url":"/paper/learning-to-rank-in-generative-retrieval","slug":"learning-to-rank-in-generative-retrieval","title":"Learning to Rank in Generative Retrieval","date":"2023-06-27","arxiv_id":"2306.15222","repositories_listed":2,"syntology":null},{"url":"/paper/situatedgen-incorporating-geographical-and-1","slug":"situatedgen-incorporating-geographical-and-1","title":"SituatedGen: Incorporating Geographical and Temporal Contexts into Generative Commonsense Reasoning","date":"2023-06-21","arxiv_id":"2306.12552","repositories_listed":2,"syntology":null},{"url":"/paper/knowledge-distillation-of-large-language","slug":"knowledge-distillation-of-large-language","title":"MiniLLM: Knowledge Distillation of Large Language Models","date":"2023-06-14","arxiv_id":"2306.08543","repositories_listed":2,"syntology":null},{"url":"/paper/h2ogpt-democratizing-large-language-models","slug":"h2ogpt-democratizing-large-language-models","title":"h2oGPT: Democratizing Large Language Models","date":"2023-06-13","arxiv_id":"2306.08161","repositories_listed":2,"syntology":null},{"url":"/paper/sequential-monte-carlo-steering-of-large","slug":"sequential-monte-carlo-steering-of-large","title":"Sequential Monte Carlo Steering of Large Language Models using Probabilistic Programs","date":"2023-06-05","arxiv_id":"2306.03081","repositories_listed":2,"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":4,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/sequential-monte-carlo-steering-of-large#ran","syntology_url":"https://syntology.ai/paper/2306.03081","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.03081"}},"official":{"repos":["probcomp/hfppl","probcomp/llamppl"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/preference-grounded-token-level-guidance-for-1","slug":"preference-grounded-token-level-guidance-for-1","title":"Preference-grounded Token-level Guidance for Language Model Fine-tuning","date":"2023-06-01","arxiv_id":"2306.00398","repositories_listed":2,"syntology":{"n":18,"n_ran":8,"n_constructed":1,"n_ran_checked":2,"n_instrument":6,"n_unverified":10,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":4,"phrase":"8 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 6 where Syntology's instrument failed) · 10 unverified","sample_list":"/paper/preference-grounded-token-level-guidance-for-1#ran","syntology_url":"https://syntology.ai/paper/2306.00398","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.00398"}},"official":{"repos":["shentao-yang/preference_grounded_guidance"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/generating-with-confidence-uncertainty","slug":"generating-with-confidence-uncertainty","title":"Generating with Confidence: Uncertainty Quantification for Black-box Large Language Models","date":"2023-05-30","arxiv_id":"2305.19187","repositories_listed":2,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/generating-with-confidence-uncertainty#ran","syntology_url":"https://syntology.ai/paper/2305.19187","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.19187"}},"official":{"repos":["zlin7/uq-nlg"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/grammar-prompting-for-domain-specific","slug":"grammar-prompting-for-domain-specific","title":"Grammar Prompting for Domain-Specific Language Generation with Large Language Models","date":"2023-05-30","arxiv_id":"2305.19234","repositories_listed":2,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":1,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/grammar-prompting-for-domain-specific#ran","syntology_url":"https://syntology.ai/paper/2305.19234","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.19234"}},"official":{"repos":["berlino/grammar-prompting"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/alignscore-evaluating-factual-consistency","slug":"alignscore-evaluating-factual-consistency","title":"AlignScore: Evaluating Factual Consistency with a Unified Alignment Function","date":"2023-05-26","arxiv_id":"2305.16739","repositories_listed":2,"syntology":null},{"url":"/paper/s4m-generating-radiology-reports-by-a-single","slug":"s4m-generating-radiology-reports-by-a-single","title":"Act Like a Radiologist: Radiology Report Generation across Anatomical Regions","date":"2023-05-26","arxiv_id":"2305.16685","repositories_listed":2,"syntology":null},{"url":"/paper/large-language-models-are-effective-table-to","slug":"large-language-models-are-effective-table-to","title":"Investigating Table-to-Text Generation Capabilities of LLMs in Real-World Information Seeking Scenarios","date":"2023-05-24","arxiv_id":"2305.14987","repositories_listed":2,"syntology":null},{"url":"/paper/not-all-metrics-are-guilty-improving-nlg","slug":"not-all-metrics-are-guilty-improving-nlg","title":"Not All Metrics Are Guilty: Improving NLG Evaluation by Diversifying References","date":"2023-05-24","arxiv_id":"2305.15067","repositories_listed":2,"syntology":null},{"url":"/paper/instructscore-towards-explainable-text","slug":"instructscore-towards-explainable-text","title":"INSTRUCTSCORE: Explainable Text Generation Evaluation with Finegrained Feedback","date":"2023-05-23","arxiv_id":"2305.14282","repositories_listed":2,"syntology":null},{"url":"/paper/qtsumm-a-new-benchmark-for-query-focused","slug":"qtsumm-a-new-benchmark-for-query-focused","title":"QTSumm: Query-Focused Summarization over Tabular Data","date":"2023-05-23","arxiv_id":"2305.14303","repositories_listed":2,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/qtsumm-a-new-benchmark-for-query-focused#ran","syntology_url":"https://syntology.ai/paper/2305.14303","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.14303"}},"official":{"repos":["yale-nlp/qtsumm","yilunzhao/qtsumm"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/chatgpt-to-replace-crowdsourcing-of","slug":"chatgpt-to-replace-crowdsourcing-of","title":"ChatGPT to Replace Crowdsourcing of Paraphrases for Intent Classification: Higher Diversity and Comparable Model Robustness","date":"2023-05-22","arxiv_id":"2305.12947","repositories_listed":2,"syntology":null},{"url":"/paper/deepfake-text-detection-in-the-wild","slug":"deepfake-text-detection-in-the-wild","title":"MAGE: Machine-generated Text Detection in the Wild","date":"2023-05-22","arxiv_id":"2305.13242","repositories_listed":2,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/deepfake-text-detection-in-the-wild#ran","syntology_url":"https://syntology.ai/paper/2305.13242","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.13242"}},"official":{"repos":["yafuly/deepfaketextdetect","yafuly/mage"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/bolt-fast-energy-based-controlled-text","slug":"bolt-fast-energy-based-controlled-text","title":"BOLT: Fast Energy-based Controlled Text Generation with Tunable Biases","date":"2023-05-19","arxiv_id":"2305.12018","repositories_listed":2,"syntology":{"n":1,"n_ran":1,"n_constructed":1,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"phrase":"1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result","sample_list":"/paper/bolt-fast-energy-based-controlled-text#ran","syntology_url":"https://syntology.ai/paper/2305.12018","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.12018"}},"official":{"repos":["launchnlp/bolt"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/llm-pruner-on-the-structural-pruning-of-large-1","slug":"llm-pruner-on-the-structural-pruning-of-large-1","title":"LLM-Pruner: On the Structural Pruning of Large Language Models","date":"2023-05-19","arxiv_id":"2305.11627","repositories_listed":2,"syntology":null},{"url":"/paper/ar-diffusion-auto-regressive-diffusion-model-1","slug":"ar-diffusion-auto-regressive-diffusion-model-1","title":"AR-Diffusion: Auto-Regressive Diffusion Model for Text Generation","date":"2023-05-16","arxiv_id":"2305.09515","repositories_listed":2,"syntology":null},{"url":"/paper/tess-text-to-text-self-conditioned-simplex","slug":"tess-text-to-text-self-conditioned-simplex","title":"TESS: Text-to-Text Self-Conditioned Simplex Diffusion","date":"2023-05-15","arxiv_id":"2305.08379","repositories_listed":2,"syntology":{"n":15,"n_ran":12,"n_constructed":0,"n_ran_checked":12,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":12,"n_pointer_only":0,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/tess-text-to-text-self-conditioned-simplex#ran","syntology_url":"https://syntology.ai/paper/2305.08379","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.08379"}},"official":{"repos":["allenai/tess-diffusion"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/gptutor-a-chatgpt-powered-programming-tool","slug":"gptutor-a-chatgpt-powered-programming-tool","title":"GPTutor: a ChatGPT-powered programming tool for code explanation","date":"2023-05-03","arxiv_id":"2305.01863","repositories_listed":2,"syntology":null},{"url":"/paper/large-language-models-are-state-of-the-art-1","slug":"large-language-models-are-state-of-the-art-1","title":"ICE-Score: Instructing Large Language Models to Evaluate Code","date":"2023-04-27","arxiv_id":"2304.14317","repositories_listed":2,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":1,"n_honours":2,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 2 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/large-language-models-are-state-of-the-art-1#ran","syntology_url":"https://syntology.ai/paper/2304.14317","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2304.14317"}},"official":{"repos":["terryyz/llm-code-eval","terryyz/ice-score"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/gpt-ner-named-entity-recognition-via-large","slug":"gpt-ner-named-entity-recognition-via-large","title":"GPT-NER: Named Entity Recognition via Large Language Models","date":"2023-04-20","arxiv_id":"2304.10428","repositories_listed":2,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/gpt-ner-named-entity-recognition-via-large#ran","syntology_url":"https://syntology.ai/paper/2304.10428","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2304.10428"}},"official":{"repos":["shuhewang1998/gpt-ner"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/longform-optimizing-instruction-tuning-for","slug":"longform-optimizing-instruction-tuning-for","title":"LongForm: Effective Instruction Tuning with Reverse Instructions","date":"2023-04-17","arxiv_id":"2304.08460","repositories_listed":2,"syntology":null},{"url":"/paper/greekbart-the-first-pretrained-greek-sequence","slug":"greekbart-the-first-pretrained-greek-sequence","title":"GreekBART: The First Pretrained Greek Sequence-to-Sequence Model","date":"2023-04-03","arxiv_id":"2304.00869","repositories_listed":2,"syntology":null},{"url":"/paper/understanding-individual-and-team-based-human","slug":"understanding-individual-and-team-based-human","title":"Does Human Collaboration Enhance the Accuracy of Identifying LLM-Generated Deepfake Texts?","date":"2023-04-03","arxiv_id":"2304.01002","repositories_listed":2,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/understanding-individual-and-team-based-human#ran","syntology_url":"https://syntology.ai/paper/2304.01002","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2304.01002"}},"official":{"repos":["huashen218/llm-deepfake-human-study"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/handwritten-text-generation-from-visual","slug":"handwritten-text-generation-from-visual","title":"Handwritten Text Generation from Visual Archetypes","date":"2023-03-27","arxiv_id":"2303.15269","repositories_listed":2,"syntology":{"n":28,"n_ran":21,"n_constructed":10,"n_ran_checked":14,"n_instrument":7,"n_unverified":7,"n_honours":1,"n_violates":0,"n_no_contract":13,"n_pointer_only":5,"phrase":"21 ran (of which 10 constructed an object rather than computing a result; 14 with no instrument failure: 1 honoured, 0 violated, 13 with no contract checked; 7 where Syntology's instrument failed) · 7 unverified","sample_list":"/paper/handwritten-text-generation-from-visual#ran","syntology_url":"https://syntology.ai/paper/2303.15269","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.15269"}},"official":{"repos":["aimagelab/vatr"],"state":"official (archive's flag): 14 ran","n_ran":14,"n_constructed":10,"n_ran_no_instrument_failure":11,"n_unverified":6,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/adaptive-budget-allocation-for-parameter","slug":"adaptive-budget-allocation-for-parameter","title":"AdaLoRA: Adaptive Budget Allocation for Parameter-Efficient Fine-Tuning","date":"2023-03-18","arxiv_id":"2303.10512","repositories_listed":2,"syntology":{"n":2,"n_ran":2,"n_constructed":1,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"2 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/adaptive-budget-allocation-for-parameter#ran","syntology_url":"https://syntology.ai/paper/2303.10512","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.10512"}},"official":{"repos":["qingruzhang/adalora"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":1,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/large-language-models-know-your-contextual","slug":"large-language-models-know-your-contextual","title":"Large Language Models Know Your Contextual Search Intent: A Prompting Framework for Conversational Search","date":"2023-03-12","arxiv_id":"2303.06573","repositories_listed":2,"syntology":null},{"url":"/paper/zeronlg-aligning-and-autoencoding-domains-for","slug":"zeronlg-aligning-and-autoencoding-domains-for","title":"ZeroNLG: Aligning and Autoencoding Domains for Zero-Shot Multimodal and Multilingual Natural Language Generation","date":"2023-03-11","arxiv_id":"2303.06458","repositories_listed":2,"syntology":null},{"url":"/paper/inseq-an-interpretability-toolkit-for","slug":"inseq-an-interpretability-toolkit-for","title":"Inseq: An Interpretability Toolkit for Sequence Generation Models","date":"2023-02-27","arxiv_id":"2302.13942","repositories_listed":2,"syntology":null}],"record_sha256":"ac2c7e7ae7b2826e1e2d3c48af9696a4ed12f060982beaaabcf37c6a621cd53d","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}