{"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/7","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":7,"pages_in_order":54,"rows_per_page":100,"rows":[601,700],"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/papers/6","next":"/task/text-generation/papers/8","papers":[{"url":"/paper/on-the-generalizability-of-foundation-models","slug":"on-the-generalizability-of-foundation-models","title":"On the Generalizability of Foundation Models for Crop Type Mapping","date":"2024-09-14","arxiv_id":"2409.09451","repositories_listed":1,"syntology":null},{"url":"/paper/transformer-with-controlled-attention-for","slug":"transformer-with-controlled-attention-for","title":"Transformer with Controlled Attention for Synchronous Motion Captioning","date":"2024-09-13","arxiv_id":"2409.09177","repositories_listed":1,"syntology":null},{"url":"/paper/enhancing-adversarial-robustness-in-natural","slug":"enhancing-adversarial-robustness-in-natural","title":"Enhancing adversarial robustness in Natural Language Inference using explanations","date":"2024-09-11","arxiv_id":"2409.07423","repositories_listed":1,"syntology":null},{"url":"/paper/ontology-free-general-domain-knowledge-graph","slug":"ontology-free-general-domain-knowledge-graph","title":"Ontology-Free General-Domain Knowledge Graph-to-Text Generation Dataset Synthesis using Large Language Model","date":"2024-09-11","arxiv_id":"2409.07088","repositories_listed":1,"syntology":{"n":7,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":4,"n_pointer_only":7,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/ontology-free-general-domain-knowledge-graph#ran","syntology_url":"https://syntology.ai/paper/2409.07088","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.07088"}},"official":{"repos":["daehuikim/WikiOFGraph"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/adversarial-attacks-on-data-attribution","slug":"adversarial-attacks-on-data-attribution","title":"Adversarial Attacks on Data Attribution","date":"2024-09-09","arxiv_id":"2409.05657","repositories_listed":1,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":1,"n_instrument":5,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":6,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 5 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/adversarial-attacks-on-data-attribution#ran","syntology_url":"https://syntology.ai/paper/2409.05657","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.05657"}},"official":{"repos":["trais-lab/adversarial-attack-data-attribution"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/diffusionpen-towards-controlling-the-style-of","slug":"diffusionpen-towards-controlling-the-style-of","title":"DiffusionPen: Towards Controlling the Style of Handwritten Text Generation","date":"2024-09-09","arxiv_id":"2409.06065","repositories_listed":1,"syntology":null},{"url":"/paper/one-shot-diffusion-mimicker-for-handwritten","slug":"one-shot-diffusion-mimicker-for-handwritten","title":"One-Shot Diffusion Mimicker for Handwritten Text Generation","date":"2024-09-06","arxiv_id":"2409.04004","repositories_listed":1,"syntology":null},{"url":"/paper/mars-a-financial-market-simulation-engine","slug":"mars-a-financial-market-simulation-engine","title":"MarS: a Financial Market Simulation Engine Powered by Generative Foundation Model","date":"2024-09-04","arxiv_id":"2409.07486","repositories_listed":1,"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/mars-a-financial-market-simulation-engine#ran","syntology_url":"https://syntology.ai/paper/2409.07486","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.07486"}},"official":{"repos":["microsoft/mars"],"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/well-that-escalated-quickly-the-single-turn","slug":"well-that-escalated-quickly-the-single-turn","title":"Well, that escalated quickly: The Single-Turn Crescendo Attack (STCA)","date":"2024-09-04","arxiv_id":"2409.03131","repositories_listed":1,"syntology":null},{"url":"/paper/clibe-detecting-dynamic-backdoors-in","slug":"clibe-detecting-dynamic-backdoors-in","title":"CLIBE: Detecting Dynamic Backdoors in Transformer-based NLP Models","date":"2024-09-02","arxiv_id":"2409.01193","repositories_listed":1,"syntology":{"n":19,"n_ran":13,"n_constructed":0,"n_ran_checked":11,"n_instrument":2,"n_unverified":6,"n_honours":0,"n_violates":0,"n_no_contract":11,"n_pointer_only":3,"phrase":"13 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; 2 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/clibe-detecting-dynamic-backdoors-in#ran","syntology_url":"https://syntology.ai/paper/2409.01193","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.01193"}},"official":{"repos":["raytsang123/clibe"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":6,"ran_from_kinds":["official"]}}},{"url":"/paper/masked-mixers-for-language-generation-and","slug":"masked-mixers-for-language-generation-and","title":"Masked Mixers for Language Generation and Retrieval","date":"2024-09-02","arxiv_id":"2409.01482","repositories_listed":1,"syntology":null},{"url":"/paper/fisher-information-guided-purification","slug":"fisher-information-guided-purification","title":"Fisher Information guided Purification against Backdoor Attacks","date":"2024-09-01","arxiv_id":"2409.00863","repositories_listed":1,"syntology":null},{"url":"/paper/memlong-memory-augmented-retrieval-for-long","slug":"memlong-memory-augmented-retrieval-for-long","title":"MemLong: Memory-Augmented Retrieval for Long Text Modeling","date":"2024-08-30","arxiv_id":"2408.16967","repositories_listed":1,"syntology":{"n":7,"n_ran":5,"n_constructed":0,"n_ran_checked":2,"n_instrument":3,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":7,"phrase":"5 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; 3 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/memlong-memory-augmented-retrieval-for-long#ran","syntology_url":"https://syntology.ai/paper/2408.16967","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.16967"}},"official":{"repos":["bui1dmysea/memlong"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/training-ultra-long-context-language-model","slug":"training-ultra-long-context-language-model","title":"Training Ultra Long Context Language Model with Fully Pipelined Distributed Transformer","date":"2024-08-30","arxiv_id":"2408.16978","repositories_listed":1,"syntology":null},{"url":"/paper/the-unreasonable-ineffectiveness-of-nucleus","slug":"the-unreasonable-ineffectiveness-of-nucleus","title":"The Unreasonable Ineffectiveness of Nucleus Sampling on Mitigating Text Memorization","date":"2024-08-29","arxiv_id":"2408.16345","repositories_listed":1,"syntology":{"n":11,"n_ran":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":1,"n_no_contract":7,"n_pointer_only":11,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 1 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/the-unreasonable-ineffectiveness-of-nucleus#ran","syntology_url":"https://syntology.ai/paper/2408.16345","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.16345"}},"official":{"repos":["lukaborec/memorization-nucleus-sampling"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/cbf-llm-safe-control-for-llm-alignment","slug":"cbf-llm-safe-control-for-llm-alignment","title":"CBF-LLM: Safe Control for LLM Alignment","date":"2024-08-28","arxiv_id":"2408.15625","repositories_listed":1,"syntology":null},{"url":"/paper/modoc-a-modular-interface-for-flexible","slug":"modoc-a-modular-interface-for-flexible","title":"MODOC: A Modular Interface for Flexible Interlinking of Text Retrieval and Text Generation Functions","date":"2024-08-26","arxiv_id":"2408.14623","repositories_listed":1,"syntology":null},{"url":"/paper/balancing-diversity-and-risk-in-llm-sampling","slug":"balancing-diversity-and-risk-in-llm-sampling","title":"Balancing Diversity and Risk in LLM Sampling: How to Select Your Method and Parameter for Open-Ended Text Generation","date":"2024-08-24","arxiv_id":"2408.13586","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":1,"n_instrument":3,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":4,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/balancing-diversity-and-risk-in-llm-sampling#ran","syntology_url":"https://syntology.ai/paper/2408.13586","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.13586"}},"official":{"repos":["ZhouYuxuanYX/Benchmarking-and-Guiding-Adaptive-Sampling-Decoding-for-LLMs"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/backdoorllm-a-comprehensive-benchmark-for","slug":"backdoorllm-a-comprehensive-benchmark-for","title":"BackdoorLLM: A Comprehensive Benchmark for Backdoor Attacks and Defenses on Large Language Models","date":"2024-08-23","arxiv_id":"2408.12798","repositories_listed":1,"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/backdoorllm-a-comprehensive-benchmark-for#ran","syntology_url":"https://syntology.ai/paper/2408.12798","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.12798"}},"official":{"repos":["bboylyg/backdoorllm"],"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/controllable-text-generation-for-large","slug":"controllable-text-generation-for-large","title":"Controllable Text Generation for Large Language Models: A Survey","date":"2024-08-22","arxiv_id":"2408.12599","repositories_listed":1,"syntology":null},{"url":"/paper/gendercare-a-comprehensive-framework-for","slug":"gendercare-a-comprehensive-framework-for","title":"GenderCARE: A Comprehensive Framework for Assessing and Reducing Gender Bias in Large Language Models","date":"2024-08-22","arxiv_id":"2408.12494","repositories_listed":1,"syntology":null},{"url":"/paper/mdd-5k-a-new-diagnostic-conversation-dataset","slug":"mdd-5k-a-new-diagnostic-conversation-dataset","title":"MDD-5k: A New Diagnostic Conversation Dataset for Mental Disorders Synthesized via Neuro-Symbolic LLM Agents","date":"2024-08-22","arxiv_id":"2408.12142","repositories_listed":1,"syntology":null},{"url":"/paper/preference-guided-reflective-sampling-for","slug":"preference-guided-reflective-sampling-for","title":"Preference-Guided Reflective Sampling for Aligning Language Models","date":"2024-08-22","arxiv_id":"2408.12163","repositories_listed":1,"syntology":null},{"url":"/paper/unifashion-a-unified-vision-language-model","slug":"unifashion-a-unified-vision-language-model","title":"UniFashion: A Unified Vision-Language Model for Multimodal Fashion Retrieval and Generation","date":"2024-08-21","arxiv_id":"2408.11305","repositories_listed":1,"syntology":{"n":11,"n_ran":8,"n_constructed":0,"n_ran_checked":7,"n_instrument":1,"n_unverified":3,"n_honours":1,"n_violates":1,"n_no_contract":5,"n_pointer_only":11,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 1 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/unifashion-a-unified-vision-language-model#ran","syntology_url":"https://syntology.ai/paper/2408.11305","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.11305"}},"official":{"repos":["xiangyu-mm/unifashion"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/customizing-language-models-with-instance","slug":"customizing-language-models-with-instance","title":"Customizing Language Models with Instance-wise LoRA for Sequential Recommendation","date":"2024-08-19","arxiv_id":"2408.10159","repositories_listed":1,"syntology":{"n":13,"n_ran":8,"n_constructed":7,"n_ran_checked":7,"n_instrument":1,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":13,"phrase":"8 ran (of which 7 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) · 5 unverified","sample_list":"/paper/customizing-language-models-with-instance#ran","syntology_url":"https://syntology.ai/paper/2408.10159","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.10159"}},"official":{"repos":["akalikong/ilora"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":7,"n_ran_no_instrument_failure":7,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/goldfish-monolingual-language-models-for-350","slug":"goldfish-monolingual-language-models-for-350","title":"Goldfish: Monolingual Language Models for 350 Languages","date":"2024-08-19","arxiv_id":"2408.10441","repositories_listed":1,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"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 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) · 1 unverified","sample_list":"/paper/goldfish-monolingual-language-models-for-350#ran","syntology_url":"https://syntology.ai/paper/2408.10441","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.10441"}},"official":{"repos":["tylerachang/goldfish"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/r2gencsr-retrieving-context-samples-for-large","slug":"r2gencsr-retrieving-context-samples-for-large","title":"R2GenCSR: Retrieving Context Samples for Large Language Model based X-ray Medical Report Generation","date":"2024-08-19","arxiv_id":"2408.09743","repositories_listed":1,"syntology":null},{"url":"/paper/smile-zero-shot-sparse-mixture-of-low-rank","slug":"smile-zero-shot-sparse-mixture-of-low-rank","title":"SMILE: Zero-Shot Sparse Mixture of Low-Rank Experts Construction From Pre-Trained Foundation Models","date":"2024-08-19","arxiv_id":"2408.10174","repositories_listed":1,"syntology":null},{"url":"/paper/automatic-metrics-in-natural-language","slug":"automatic-metrics-in-natural-language","title":"Automatic Metrics in Natural Language Generation: A Survey of Current Evaluation Practices","date":"2024-08-17","arxiv_id":"2408.09169","repositories_listed":1,"syntology":null},{"url":"/paper/an-end-to-end-model-for-photo-sharing-multi","slug":"an-end-to-end-model-for-photo-sharing-multi","title":"An End-to-End Model for Photo-Sharing Multi-modal Dialogue Generation","date":"2024-08-16","arxiv_id":"2408.08650","repositories_listed":1,"syntology":null},{"url":"/paper/ecg-chat-a-large-ecg-language-model-for","slug":"ecg-chat-a-large-ecg-language-model-for","title":"ECG-Chat: A Large ECG-Language Model for Cardiac Disease Diagnosis","date":"2024-08-16","arxiv_id":"2408.08849","repositories_listed":1,"syntology":{"n":14,"n_ran":6,"n_constructed":0,"n_ran_checked":4,"n_instrument":2,"n_unverified":8,"n_honours":0,"n_violates":1,"n_no_contract":3,"n_pointer_only":14,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 1 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 8 unverified","sample_list":"/paper/ecg-chat-a-large-ecg-language-model-for#ran","syntology_url":"https://syntology.ai/paper/2408.08849","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.08849"}},"official":{"repos":["YubaoZhao/ECG-Chat"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":8,"ran_from_kinds":["official"]}}},{"url":"/paper/emodynamix-emotional-support-dialogue","slug":"emodynamix-emotional-support-dialogue","title":"EmoDynamiX: Emotional Support Dialogue Strategy Prediction by Modelling MiXed Emotions and Discourse Dynamics","date":"2024-08-16","arxiv_id":"2408.08782","repositories_listed":1,"syntology":null},{"url":"/paper/coupling-without-communication-and-drafter","slug":"coupling-without-communication-and-drafter","title":"Coupling without Communication and Drafter-Invariant Speculative Decoding","date":"2024-08-15","arxiv_id":"2408.07978","repositories_listed":1,"syntology":{"n":8,"n_ran":7,"n_constructed":0,"n_ran_checked":2,"n_instrument":5,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":8,"phrase":"7 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; 5 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/coupling-without-communication-and-drafter#ran","syntology_url":"https://syntology.ai/paper/2408.07978","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.07978"}},"official":{"repos":["majid-daliri/disd"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/exploring-retrieval-augmented-generation-in","slug":"exploring-retrieval-augmented-generation-in","title":"Exploring Retrieval Augmented Generation in Arabic","date":"2024-08-14","arxiv_id":"2408.07425","repositories_listed":1,"syntology":null},{"url":"/paper/parallel-speculative-decoding-with-adaptive","slug":"parallel-speculative-decoding-with-adaptive","title":"Parallel Speculative Decoding with Adaptive Draft Length","date":"2024-08-13","arxiv_id":"2408.11850","repositories_listed":1,"syntology":{"n":8,"n_ran":8,"n_constructed":0,"n_ran_checked":3,"n_instrument":5,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":2,"n_pointer_only":8,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 5 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/parallel-speculative-decoding-with-adaptive#ran","syntology_url":"https://syntology.ai/paper/2408.11850","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.11850"}},"official":{"repos":["smart-lty/parallelspeculativedecoding"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/towards-robust-and-cost-efficient-knowledge","slug":"towards-robust-and-cost-efficient-knowledge","title":"Towards Robust and Parameter-Efficient Knowledge Unlearning for LLMs","date":"2024-08-13","arxiv_id":"2408.06621","repositories_listed":1,"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":0,"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/towards-robust-and-cost-efficient-knowledge#ran","syntology_url":"https://syntology.ai/paper/2408.06621","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.06621"}},"official":{"repos":["csm9493/efficient-llm-unlearning"],"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/adtec-a-unified-benchmark-for-evaluating-text","slug":"adtec-a-unified-benchmark-for-evaluating-text","title":"AdTEC: A Unified Benchmark for Evaluating Text Quality in Search Engine Advertising","date":"2024-08-12","arxiv_id":"2408.05906","repositories_listed":1,"syntology":null},{"url":"/paper/an-evaluation-of-standard-statistical-models","slug":"an-evaluation-of-standard-statistical-models","title":"An Evaluation of Standard Statistical Models and LLMs on Time Series Forecasting","date":"2024-08-09","arxiv_id":"2408.04867","repositories_listed":1,"syntology":null},{"url":"/paper/bias-aware-low-rank-adaptation-mitigating","slug":"bias-aware-low-rank-adaptation-mitigating","title":"BA-LoRA: Bias-Alleviating Low-Rank Adaptation to Mitigate Catastrophic Inheritance in Large Language Models","date":"2024-08-08","arxiv_id":"2408.04556","repositories_listed":1,"syntology":{"n":13,"n_ran":12,"n_constructed":0,"n_ran_checked":10,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":1,"n_no_contract":9,"n_pointer_only":13,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 1 violated, 9 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/bias-aware-low-rank-adaptation-mitigating#ran","syntology_url":"https://syntology.ai/paper/2408.04556","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.04556"}},"official":{"repos":["cyp-jlu-ai/ba-lora"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/diffusion-guided-language-modeling","slug":"diffusion-guided-language-modeling","title":"Diffusion Guided Language Modeling","date":"2024-08-08","arxiv_id":"2408.04220","repositories_listed":1,"syntology":{"n":15,"n_ran":14,"n_constructed":0,"n_ran_checked":13,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":2,"n_no_contract":11,"n_pointer_only":1,"phrase":"14 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 0 honoured, 2 violated, 11 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/diffusion-guided-language-modeling#ran","syntology_url":"https://syntology.ai/paper/2408.04220","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.04220"}},"official":{"repos":["justinlovelace/diffusion-guided-lm"],"state":"official (archive's flag): 14 ran","n_ran":14,"n_constructed":0,"n_ran_no_instrument_failure":13,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/mbrs-a-library-for-minimum-bayes-risk","slug":"mbrs-a-library-for-minimum-bayes-risk","title":"mbrs: A Library for Minimum Bayes Risk Decoding","date":"2024-08-08","arxiv_id":"2408.04167","repositories_listed":1,"syntology":null},{"url":"/paper/human-speech-perception-in-noise-can-large","slug":"human-speech-perception-in-noise-can-large","title":"Human Speech Perception in Noise: Can Large Language Models Paraphrase to Improve It?","date":"2024-08-07","arxiv_id":"2408.04029","repositories_listed":1,"syntology":null},{"url":"/paper/openstory-a-large-scale-dataset-and-benchmark","slug":"openstory-a-large-scale-dataset-and-benchmark","title":"Openstory++: A Large-scale Dataset and Benchmark for Instance-aware Open-domain Visual Storytelling","date":"2024-08-07","arxiv_id":"2408.03695","repositories_listed":1,"syntology":null},{"url":"/paper/zero-shot-factual-consistency-evaluation","slug":"zero-shot-factual-consistency-evaluation","title":"Zero-shot Factual Consistency Evaluation Across Domains","date":"2024-08-07","arxiv_id":"2408.04114","repositories_listed":1,"syntology":null},{"url":"/paper/2408-02976","slug":"2408-02976","title":"Empathy Level Alignment via Reinforcement Learning for Empathetic Response Generation","date":"2024-08-06","arxiv_id":"2408.02976","repositories_listed":1,"syntology":null},{"url":"/paper/2408-02056","slug":"2408-02056","title":"MedSyn: LLM-based Synthetic Medical Text Generation Framework","date":"2024-08-04","arxiv_id":"2408.02056","repositories_listed":1,"syntology":null},{"url":"/paper/2408-01394","slug":"2408-01394","title":"Improving Multilingual Neural Machine Translation by Utilizing Semantic and Linguistic Features","date":"2024-08-02","arxiv_id":"2408.01394","repositories_listed":1,"syntology":null},{"url":"/paper/2408-00312","slug":"2408-00312","title":"Adversarial Text Rewriting for Text-aware Recommender Systems","date":"2024-08-01","arxiv_id":"2408.00312","repositories_listed":1,"syntology":null},{"url":"/paper/2408-00765","slug":"2408-00765","title":"MM-Vet v2: A Challenging Benchmark to Evaluate Large Multimodal Models for Integrated Capabilities","date":"2024-08-01","arxiv_id":"2408.00765","repositories_listed":1,"syntology":{"n":6,"n_ran":4,"n_constructed":0,"n_ran_checked":0,"n_instrument":4,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"4 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; 4 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/2408-00765#ran","syntology_url":"https://syntology.ai/paper/2408.00765","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.00765"}},"official":{"repos":["yuweihao/mm-vet"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/paying-more-attention-to-image-a-training","slug":"paying-more-attention-to-image-a-training","title":"Paying More Attention to Image: A Training-Free Method for Alleviating Hallucination in LVLMs","date":"2024-07-31","arxiv_id":"2407.21771","repositories_listed":1,"syntology":{"n":7,"n_ran":7,"n_constructed":0,"n_ran_checked":4,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":3,"n_pointer_only":1,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 1 violated, 3 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/paying-more-attention-to-image-a-training#ran","syntology_url":"https://syntology.ai/paper/2407.21771","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.21771"}},"official":null}},{"url":"/paper/adaptive-contrastive-search-uncertainty","slug":"adaptive-contrastive-search-uncertainty","title":"Adaptive Contrastive Search: Uncertainty-Guided Decoding for Open-Ended Text Generation","date":"2024-07-26","arxiv_id":"2407.18698","repositories_listed":1,"syntology":null},{"url":"/paper/efficient-inference-of-vision-instruction","slug":"efficient-inference-of-vision-instruction","title":"Efficient Inference of Vision Instruction-Following Models with Elastic Cache","date":"2024-07-25","arxiv_id":"2407.18121","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":1,"n_ran_checked":2,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"5 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; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/efficient-inference-of-vision-instruction#ran","syntology_url":"https://syntology.ai/paper/2407.18121","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.18121"}},"official":{"repos":["liuzuyan/elasticcache"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":1,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/positive-text-reframing-under-multi-strategy","slug":"positive-text-reframing-under-multi-strategy","title":"Positive Text Reframing under Multi-strategy Optimization","date":"2024-07-25","arxiv_id":"2407.17940","repositories_listed":1,"syntology":null},{"url":"/paper/finetuning-generative-large-language-models","slug":"finetuning-generative-large-language-models","title":"Finetuning Generative Large Language Models with Discrimination Instructions for Knowledge Graph Completion","date":"2024-07-23","arxiv_id":"2407.16127","repositories_listed":1,"syntology":null},{"url":"/paper/harmonizing-visual-text-comprehension-and","slug":"harmonizing-visual-text-comprehension-and","title":"Harmonizing Visual Text Comprehension and Generation","date":"2024-07-23","arxiv_id":"2407.16364","repositories_listed":1,"syntology":{"n":18,"n_ran":11,"n_constructed":0,"n_ran_checked":7,"n_instrument":4,"n_unverified":7,"n_honours":1,"n_violates":0,"n_no_contract":6,"n_pointer_only":0,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 0 violated, 6 with no contract checked; 4 where Syntology's instrument failed) · 7 unverified","sample_list":"/paper/harmonizing-visual-text-comprehension-and#ran","syntology_url":"https://syntology.ai/paper/2407.16364","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.16364"}},"official":{"repos":["bytedance/textharmony"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":7,"ran_from_kinds":["official"]}}},{"url":"/paper/retrieve-generate-evaluate-a-case-study-for","slug":"retrieve-generate-evaluate-a-case-study-for","title":"Retrieve, Generate, Evaluate: A Case Study for Medical Paraphrases Generation with Small Language Models","date":"2024-07-23","arxiv_id":"2407.16565","repositories_listed":1,"syntology":null},{"url":"/paper/robust-privacy-amidst-innovation-with-large","slug":"robust-privacy-amidst-innovation-with-large","title":"Robust Privacy Amidst Innovation with Large Language Models Through a Critical Assessment of the Risks","date":"2024-07-23","arxiv_id":"2407.16166","repositories_listed":1,"syntology":null},{"url":"/paper/promises-and-pitfalls-of-generative-masked","slug":"promises-and-pitfalls-of-generative-masked","title":"Promises and Pitfalls of Generative Masked Language Modeling: Theoretical Framework and Practical Guidelines","date":"2024-07-22","arxiv_id":"2407.21046","repositories_listed":1,"syntology":null},{"url":"/paper/intelligent-artistic-typography-a","slug":"intelligent-artistic-typography-a","title":"Intelligent Artistic Typography: A Comprehensive Review of Artistic Text Design and Generation","date":"2024-07-20","arxiv_id":"2407.14774","repositories_listed":1,"syntology":null},{"url":"/paper/visual-text-generation-in-the-wild","slug":"visual-text-generation-in-the-wild","title":"Visual Text Generation in the Wild","date":"2024-07-19","arxiv_id":"2407.14138","repositories_listed":1,"syntology":null},{"url":"/paper/villa-video-reasoning-segmentation-with-large","slug":"villa-video-reasoning-segmentation-with-large","title":"ViLLa: Video Reasoning Segmentation with Large Language Model","date":"2024-07-18","arxiv_id":"2407.14500","repositories_listed":1,"syntology":null},{"url":"/paper/how-control-information-influences","slug":"how-control-information-influences","title":"How Control Information Influences Multilingual Text Image Generation and Editing?","date":"2024-07-16","arxiv_id":"2407.11502","repositories_listed":1,"syntology":null},{"url":"/paper/masive-open-ended-affective-state","slug":"masive-open-ended-affective-state","title":"MASIVE: Open-Ended Affective State Identification in English and Spanish","date":"2024-07-16","arxiv_id":"2407.12196","repositories_listed":1,"syntology":null},{"url":"/paper/what-s-wrong-refining-meeting-summaries-with","slug":"what-s-wrong-refining-meeting-summaries-with","title":"What's Wrong? Refining Meeting Summaries with LLM Feedback","date":"2024-07-16","arxiv_id":"2407.11919","repositories_listed":1,"syntology":null},{"url":"/paper/enriching-information-and-preserving-semantic","slug":"enriching-information-and-preserving-semantic","title":"Enriching Information and Preserving Semantic Consistency in Expanding Curvilinear Object Segmentation Datasets","date":"2024-07-11","arxiv_id":"2407.08209","repositories_listed":1,"syntology":null},{"url":"/paper/seed-story-multimodal-long-story-generation","slug":"seed-story-multimodal-long-story-generation","title":"SEED-Story: Multimodal Long Story Generation with Large Language Model","date":"2024-07-11","arxiv_id":"2407.08683","repositories_listed":1,"syntology":{"n":17,"n_ran":14,"n_constructed":0,"n_ran_checked":8,"n_instrument":6,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":17,"phrase":"14 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 6 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/seed-story-multimodal-long-story-generation#ran","syntology_url":"https://syntology.ai/paper/2407.08683","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.08683"}},"official":{"repos":["tencentarc/seed-story"],"state":"official (archive's flag): 14 ran","n_ran":14,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/arabic-automatic-story-generation-with-large","slug":"arabic-automatic-story-generation-with-large","title":"Arabic Automatic Story Generation with Large Language Models","date":"2024-07-10","arxiv_id":"2407.07551","repositories_listed":1,"syntology":null},{"url":"/paper/mars-mixture-of-auto-regressive-models-for","slug":"mars-mixture-of-auto-regressive-models-for","title":"MARS: Mixture of Auto-Regressive Models for Fine-grained Text-to-image Synthesis","date":"2024-07-10","arxiv_id":"2407.07614","repositories_listed":1,"syntology":null},{"url":"/paper/rosa-random-subspace-adaptation-for-efficient","slug":"rosa-random-subspace-adaptation-for-efficient","title":"ROSA: Random Subspace Adaptation for Efficient Fine-Tuning","date":"2024-07-10","arxiv_id":"2407.07802","repositories_listed":1,"syntology":null},{"url":"/paper/anole-an-open-autoregressive-native-large","slug":"anole-an-open-autoregressive-native-large","title":"ANOLE: An Open, Autoregressive, Native Large Multimodal Models for Interleaved Image-Text Generation","date":"2024-07-08","arxiv_id":"2407.06135","repositories_listed":1,"syntology":null},{"url":"/paper/core-robust-factual-precision-scoring-with","slug":"core-robust-factual-precision-scoring-with","title":"Core: Robust Factual Precision with Informative Sub-Claim Identification","date":"2024-07-04","arxiv_id":"2407.03572","repositories_listed":1,"syntology":null},{"url":"/paper/systematic-task-exploration-with-llms-a-study","slug":"systematic-task-exploration-with-llms-a-study","title":"Systematic Task Exploration with LLMs: A Study in Citation Text Generation","date":"2024-07-04","arxiv_id":"2407.04046","repositories_listed":1,"syntology":null},{"url":"/paper/llm-internal-states-reveal-hallucination-risk","slug":"llm-internal-states-reveal-hallucination-risk","title":"LLM Internal States Reveal Hallucination Risk Faced With a Query","date":"2024-07-03","arxiv_id":"2407.03282","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"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) · 1 unverified","sample_list":"/paper/llm-internal-states-reveal-hallucination-risk#ran","syntology_url":"https://syntology.ai/paper/2407.03282","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.03282"}},"official":{"repos":["ziweiji/Internal_States_Reveal_Hallucination"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/extracting-and-encoding-leveraging-large","slug":"extracting-and-encoding-leveraging-large","title":"Extracting and Encoding: Leveraging Large Language Models and Medical Knowledge to Enhance Radiological Text Representation","date":"2024-07-02","arxiv_id":"2407.01948","repositories_listed":1,"syntology":null},{"url":"/paper/integrate-the-essence-and-eliminate-the-dross","slug":"integrate-the-essence-and-eliminate-the-dross","title":"Integrate the Essence and Eliminate the Dross: Fine-Grained Self-Consistency for Free-Form Language Generation","date":"2024-07-02","arxiv_id":"2407.02056","repositories_listed":1,"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/integrate-the-essence-and-eliminate-the-dross#ran","syntology_url":"https://syntology.ai/paper/2407.02056","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.02056"}},"official":{"repos":["WangXinglin/FSC"],"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/mememo-on-device-retrieval-augmentation-for","slug":"mememo-on-device-retrieval-augmentation-for","title":"MeMemo: On-device Retrieval Augmentation for Private and Personalized Text Generation","date":"2024-07-02","arxiv_id":"2407.01972","repositories_listed":1,"syntology":null},{"url":"/paper/deep-image-to-recipe-translation","slug":"deep-image-to-recipe-translation","title":"Deep Image-to-Recipe Translation","date":"2024-07-01","arxiv_id":"2407.00911","repositories_listed":1,"syntology":null},{"url":"/paper/conu-conformal-uncertainty-in-large-language","slug":"conu-conformal-uncertainty-in-large-language","title":"ConU: Conformal Uncertainty in Large Language Models with Correctness Coverage Guarantees","date":"2024-06-29","arxiv_id":"2407.00499","repositories_listed":1,"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":1,"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/conu-conformal-uncertainty-in-large-language#ran","syntology_url":"https://syntology.ai/paper/2407.00499","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.00499"}},"official":{"repos":["zhiyuan-gg/conformal-uncertainty-criterion"],"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/infinigen-efficient-generative-inference-of","slug":"infinigen-efficient-generative-inference-of","title":"InfiniGen: Efficient Generative Inference of Large Language Models with Dynamic KV Cache Management","date":"2024-06-28","arxiv_id":"2406.19707","repositories_listed":1,"syntology":{"n":15,"n_ran":14,"n_constructed":0,"n_ran_checked":10,"n_instrument":4,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":10,"n_pointer_only":1,"phrase":"14 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 4 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/infinigen-efficient-generative-inference-of#ran","syntology_url":"https://syntology.ai/paper/2406.19707","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.19707"}},"official":null}},{"url":"/paper/can-large-language-models-generate-high","slug":"can-large-language-models-generate-high","title":"Can Large Language Models Generate High-quality Patent Claims?","date":"2024-06-27","arxiv_id":"2406.19465","repositories_listed":1,"syntology":null},{"url":"/paper/suri-multi-constraint-instruction-following","slug":"suri-multi-constraint-instruction-following","title":"Suri: Multi-constraint Instruction Following for Long-form Text Generation","date":"2024-06-27","arxiv_id":"2406.19371","repositories_listed":1,"syntology":{"n":15,"n_ran":12,"n_constructed":0,"n_ran_checked":12,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":1,"n_no_contract":11,"n_pointer_only":15,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 1 violated, 11 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/suri-multi-constraint-instruction-following#ran","syntology_url":"https://syntology.ai/paper/2406.19371","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.19371"}},"official":{"repos":["chtmp223/suri"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":12,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/veriscore-evaluating-the-factuality-of","slug":"veriscore-evaluating-the-factuality-of","title":"VERISCORE: Evaluating the factuality of verifiable claims in long-form text generation","date":"2024-06-27","arxiv_id":"2406.19276","repositories_listed":1,"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/veriscore-evaluating-the-factuality-of#ran","syntology_url":"https://syntology.ai/paper/2406.19276","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.19276"}},"official":{"repos":["Yixiao-Song/VeriScore"],"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/prexme-large-scale-prompt-exploration-of-open","slug":"prexme-large-scale-prompt-exploration-of-open","title":"PrExMe! Large Scale Prompt Exploration of Open Source LLMs for Machine Translation and Summarization Evaluation","date":"2024-06-26","arxiv_id":"2406.18528","repositories_listed":1,"syntology":null},{"url":"/paper/shimo-lab-at-discharge-me-discharge","slug":"shimo-lab-at-discharge-me-discharge","title":"Shimo Lab at \"Discharge Me!\": Discharge Summarization by Prompt-Driven Concatenation of Electronic Health Record Sections","date":"2024-06-26","arxiv_id":"2406.18094","repositories_listed":1,"syntology":null},{"url":"/paper/themis-towards-flexible-and-interpretable-nlg","slug":"themis-towards-flexible-and-interpretable-nlg","title":"Themis: A Reference-free NLG Evaluation Language Model with Flexibility and Interpretability","date":"2024-06-26","arxiv_id":"2406.18365","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":3,"n_ran_checked":3,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"5 ran (of which 3 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/themis-towards-flexible-and-interpretable-nlg#ran","syntology_url":"https://syntology.ai/paper/2406.18365","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.18365"}},"official":{"repos":["PKU-ONELab/Themis"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":3,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/can-we-trust-the-performance-evaluation-of","slug":"can-we-trust-the-performance-evaluation-of","title":"Can We Trust the Performance Evaluation of Uncertainty Estimation Methods in Text Summarization?","date":"2024-06-25","arxiv_id":"2406.17274","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"5 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; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/can-we-trust-the-performance-evaluation-of#ran","syntology_url":"https://syntology.ai/paper/2406.17274","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.17274"}},"official":{"repos":["he159ok/benchmark-of-uncertainty-estimation-methods-in-text-summarization"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/talec-teach-your-llm-to-evaluate-in-specific","slug":"talec-teach-your-llm-to-evaluate-in-specific","title":"TALEC: Teach Your LLM to Evaluate in Specific Domain with In-house Criteria by Criteria Division and Zero-shot Plus Few-shot","date":"2024-06-25","arxiv_id":"2407.10999","repositories_listed":1,"syntology":null},{"url":"/paper/variationist-exploring-multifaceted-variation","slug":"variationist-exploring-multifaceted-variation","title":"Variationist: Exploring Multifaceted Variation and Bias in Written Language Data","date":"2024-06-25","arxiv_id":"2406.17647","repositories_listed":1,"syntology":{"n":3,"n_ran":1,"n_constructed":1,"n_ran_checked":1,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"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) · 2 unverified; the one sample that ran constructed an object rather than computing a result","sample_list":"/paper/variationist-exploring-multifaceted-variation#ran","syntology_url":"https://syntology.ai/paper/2406.17647","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.17647"}},"official":{"repos":["dhfbk/variationist"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/cascade-reward-sampling-for-efficient","slug":"cascade-reward-sampling-for-efficient","title":"Cascade Reward Sampling for Efficient Decoding-Time Alignment","date":"2024-06-24","arxiv_id":"2406.16306","repositories_listed":1,"syntology":{"n":10,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":10,"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) · 3 unverified","sample_list":"/paper/cascade-reward-sampling-for-efficient#ran","syntology_url":"https://syntology.ai/paper/2406.16306","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.16306"}},"official":{"repos":["lblaoke/CARDS"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/evaluation-of-language-models-in-the-medical","slug":"evaluation-of-language-models-in-the-medical","title":"Evaluation of Language Models in the Medical Context Under Resource-Constrained Settings","date":"2024-06-24","arxiv_id":"2406.16611","repositories_listed":1,"syntology":null},{"url":"/paper/revisiting-interpolation-augmentation-for","slug":"revisiting-interpolation-augmentation-for","title":"Revisiting Interpolation Augmentation for Speech-to-Text Generation","date":"2024-06-22","arxiv_id":"2406.15846","repositories_listed":1,"syntology":null},{"url":"/paper/a-tale-of-trust-and-accuracy-base-vs-instruct","slug":"a-tale-of-trust-and-accuracy-base-vs-instruct","title":"A Tale of Trust and Accuracy: Base vs. Instruct LLMs in RAG Systems","date":"2024-06-21","arxiv_id":"2406.14972","repositories_listed":1,"syntology":null},{"url":"/paper/evaluating-diversity-in-automatic-poetry","slug":"evaluating-diversity-in-automatic-poetry","title":"Evaluating Diversity in Automatic Poetry Generation","date":"2024-06-21","arxiv_id":"2406.15267","repositories_listed":1,"syntology":{"n":14,"n_ran":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":6,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":14,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/evaluating-diversity-in-automatic-poetry#ran","syntology_url":"https://syntology.ai/paper/2406.15267","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.15267"}},"official":{"repos":["hgroener/diversity_in_poetry_generation"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":6,"ran_from_kinds":["official"]}}},{"url":"/paper/tinystyler-efficient-few-shot-text-style","slug":"tinystyler-efficient-few-shot-text-style","title":"TinyStyler: Efficient Few-Shot Text Style Transfer with Authorship Embeddings","date":"2024-06-21","arxiv_id":"2406.15586","repositories_listed":1,"syntology":null},{"url":"/paper/a-data-driven-guided-decoding-mechanism-for","slug":"a-data-driven-guided-decoding-mechanism-for","title":"A Data-Driven Guided Decoding Mechanism for Diagnostic Captioning","date":"2024-06-20","arxiv_id":"2406.14164","repositories_listed":1,"syntology":null},{"url":"/paper/citygpt-empowering-urban-spatial-cognition-of","slug":"citygpt-empowering-urban-spatial-cognition-of","title":"CityGPT: Empowering Urban Spatial Cognition of Large Language Models","date":"2024-06-20","arxiv_id":"2406.13948","repositories_listed":1,"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":0,"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/citygpt-empowering-urban-spatial-cognition-of#ran","syntology_url":"https://syntology.ai/paper/2406.13948","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.13948"}},"official":{"repos":["tsinghua-fib-lab/citygpt"],"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/in-tree-structure-should-sentence-be","slug":"in-tree-structure-should-sentence-be","title":"In Tree Structure Should Sentence Be Generated","date":"2024-06-20","arxiv_id":"2406.14189","repositories_listed":1,"syntology":null},{"url":"/paper/adaptable-logical-control-for-large-language","slug":"adaptable-logical-control-for-large-language","title":"Adaptable Logical Control for Large Language Models","date":"2024-06-19","arxiv_id":"2406.13892","repositories_listed":1,"syntology":{"n":16,"n_ran":12,"n_constructed":0,"n_ran_checked":12,"n_instrument":0,"n_unverified":4,"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) · 4 unverified","sample_list":"/paper/adaptable-logical-control-for-large-language#ran","syntology_url":"https://syntology.ai/paper/2406.13892","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.13892"}},"official":{"repos":["joshuacnf/Ctrl-G"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":12,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/clinicallab-aligning-agents-for-multi","slug":"clinicallab-aligning-agents-for-multi","title":"ClinicalLab: Aligning Agents for Multi-Departmental Clinical Diagnostics in the Real World","date":"2024-06-19","arxiv_id":"2406.13890","repositories_listed":1,"syntology":null},{"url":"/paper/finding-blind-spots-in-evaluator-llms-with","slug":"finding-blind-spots-in-evaluator-llms-with","title":"Finding Blind Spots in Evaluator LLMs with Interpretable Checklists","date":"2024-06-19","arxiv_id":"2406.13439","repositories_listed":1,"syntology":null}],"record_sha256":"3c73437e61008dc3a665956dee5a527f788fc15014d82cd168a93c2f8472752c","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}