{"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/language-modelling/papers/48","list_of":"/task/language-modelling","task":"Language Modelling","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":48,"pages_in_order":177,"rows_per_page":100,"rows":[4701,4800],"of":17610,"counts":{"archive_papers_tagged":17610,"with_a_code_link":7012,"where_syntology_ran_a_sample":2428,"not_listed_spam_title":0,"listed":17610,"listed_where_code_ran":2428,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":2027,"every_run_a_failure_of_syntologys_instrument":401,"listed_with_a_run_with_no_instrument_failure":2027,"listed_every_run_a_failure_of_syntologys_instrument":401,"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/language-modelling","prev":"/task/language-modelling/papers/47","next":"/task/language-modelling/papers/49","papers":[{"url":"/paper/adapterem-pre-trained-language-model","slug":"adapterem-pre-trained-language-model","title":"AdapterEM: Pre-trained Language Model Adaptation for Generalized Entity Matching using Adapter-tuning","date":"2023-05-30","arxiv_id":"2305.18725","repositories_listed":1,"syntology":null},{"url":"/paper/empirical-sufficiency-lower-bounds-for","slug":"empirical-sufficiency-lower-bounds-for","title":"Empirical Sufficiency Lower Bounds for Language Modeling with Locally-Bootstrapped Semantic Structures","date":"2023-05-30","arxiv_id":"2305.18915","repositories_listed":1,"syntology":null},{"url":"/paper/gpt4tools-teaching-large-language-model-to","slug":"gpt4tools-teaching-large-language-model-to","title":"GPT4Tools: Teaching Large Language Model to Use Tools via Self-instruction","date":"2023-05-30","arxiv_id":"2305.18752","repositories_listed":1,"syntology":null},{"url":"/paper/likelihood-based-diffusion-language-models-1","slug":"likelihood-based-diffusion-language-models-1","title":"Likelihood-Based Diffusion Language Models","date":"2023-05-30","arxiv_id":"2305.18619","repositories_listed":1,"syntology":null},{"url":"/paper/preserving-pre-trained-features-helps","slug":"preserving-pre-trained-features-helps","title":"Preserving Pre-trained Features Helps Calibrate Fine-tuned Language Models","date":"2023-05-30","arxiv_id":"2305.19249","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":1,"phrase":"0 ran · 1 unverified","sample_list":"/paper/preserving-pre-trained-features-helps#ran","syntology_url":"https://syntology.ai/paper/2305.19249","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.19249"}},"official":{"repos":["thu-ml/lm-calibration"],"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/adapting-learned-sparse-retrieval-for-long","slug":"adapting-learned-sparse-retrieval-for-long","title":"Adapting Learned Sparse Retrieval for Long Documents","date":"2023-05-29","arxiv_id":"2305.18494","repositories_listed":1,"syntology":null},{"url":"/paper/do-language-models-know-when-they-re","slug":"do-language-models-know-when-they-re","title":"Do Language Models Know When They're Hallucinating References?","date":"2023-05-29","arxiv_id":"2305.18248","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":1,"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; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/do-language-models-know-when-they-re#ran","syntology_url":"https://syntology.ai/paper/2305.18248","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.18248"}},"official":{"repos":["microsoft/hallucinated-references"],"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/instructedit-improving-automatic-masks-for","slug":"instructedit-improving-automatic-masks-for","title":"InstructEdit: Improving Automatic Masks for Diffusion-based Image Editing With User Instructions","date":"2023-05-29","arxiv_id":"2305.18047","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/instructedit-improving-automatic-masks-for#ran","syntology_url":"https://syntology.ai/paper/2305.18047","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.18047"}},"official":{"repos":["qianwangx/instructedit"],"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/large-language-models-are-not-fair-evaluators","slug":"large-language-models-are-not-fair-evaluators","title":"Large Language Models are not Fair Evaluators","date":"2023-05-29","arxiv_id":"2305.17926","repositories_listed":1,"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/large-language-models-are-not-fair-evaluators#ran","syntology_url":"https://syntology.ai/paper/2305.17926","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.17926"}},"official":{"repos":["i-eval/faireval"],"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/leveraging-training-data-in-few-shot","slug":"leveraging-training-data-in-few-shot","title":"Leveraging Training Data in Few-Shot Prompting for Numerical Reasoning","date":"2023-05-29","arxiv_id":"2305.18170","repositories_listed":1,"syntology":null},{"url":"/paper/test-time-training-on-nearest-neighbors-for","slug":"test-time-training-on-nearest-neighbors-for","title":"Test-Time Training on Nearest Neighbors for Large Language Models","date":"2023-05-29","arxiv_id":"2305.18466","repositories_listed":1,"syntology":{"n":5,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"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) · 2 unverified","sample_list":"/paper/test-time-training-on-nearest-neighbors-for#ran","syntology_url":"https://syntology.ai/paper/2305.18466","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.18466"}},"official":{"repos":["socialfoundations/tttlm"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/the-rise-of-ai-language-pathologists","slug":"the-rise-of-ai-language-pathologists","title":"The Rise of AI Language Pathologists: Exploring Two-level Prompt Learning for Few-shot Weakly-supervised Whole Slide Image Classification","date":"2023-05-29","arxiv_id":"2305.17891","repositories_listed":1,"syntology":{"n":6,"n_ran":4,"n_constructed":2,"n_ran_checked":3,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":1,"n_no_contract":2,"n_pointer_only":6,"phrase":"4 ran (of which 2 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 1 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/the-rise-of-ai-language-pathologists#ran","syntology_url":"https://syntology.ai/paper/2305.17891","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.17891"}},"official":{"repos":["miccaiif/top"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":2,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/fusecap-leveraging-large-language-models-to","slug":"fusecap-leveraging-large-language-models-to","title":"FuseCap: Leveraging Large Language Models for Enriched Fused Image Captions","date":"2023-05-28","arxiv_id":"2305.17718","repositories_listed":1,"syntology":null},{"url":"/paper/generating-edu-extracts-for-plan-guided","slug":"generating-edu-extracts-for-plan-guided","title":"Generating EDU Extracts for Plan-Guided Summary Re-Ranking","date":"2023-05-28","arxiv_id":"2305.17779","repositories_listed":1,"syntology":{"n":10,"n_ran":6,"n_constructed":0,"n_ran_checked":0,"n_instrument":6,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":10,"phrase":"6 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; 6 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/generating-edu-extracts-for-plan-guided#ran","syntology_url":"https://syntology.ai/paper/2305.17779","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.17779"}},"official":{"repos":["griff4692/edu-sum"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/kosbi-a-dataset-for-mitigating-social-bias","slug":"kosbi-a-dataset-for-mitigating-social-bias","title":"KoSBi: A Dataset for Mitigating Social Bias Risks Towards Safer Large Language Model Application","date":"2023-05-28","arxiv_id":"2305.17701","repositories_listed":1,"syntology":null},{"url":"/paper/learning-a-structural-causal-model-for","slug":"learning-a-structural-causal-model-for","title":"Learning a Structural Causal Model for Intuition Reasoning in Conversation","date":"2023-05-28","arxiv_id":"2305.17727","repositories_listed":1,"syntology":null},{"url":"/paper/rethinking-masked-language-modeling-for","slug":"rethinking-masked-language-modeling-for","title":"Rethinking Masked Language Modeling for Chinese Spelling Correction","date":"2023-05-28","arxiv_id":"2305.17721","repositories_listed":1,"syntology":null},{"url":"/paper/improving-generalization-in-language-model","slug":"improving-generalization-in-language-model","title":"Improving Generalization in Language Model-Based Text-to-SQL Semantic Parsing: Two Simple Semantic Boundary-Based Techniques","date":"2023-05-27","arxiv_id":"2305.17378","repositories_listed":1,"syntology":null},{"url":"/paper/query-efficient-black-box-red-teaming-via","slug":"query-efficient-black-box-red-teaming-via","title":"Query-Efficient Black-Box Red Teaming via Bayesian Optimization","date":"2023-05-27","arxiv_id":"2305.17444","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/query-efficient-black-box-red-teaming-via#ran","syntology_url":"https://syntology.ai/paper/2305.17444","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.17444"}},"official":{"repos":["snu-mllab/bayesian-red-teaming"],"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/an-empirical-comparison-of-lm-based-question","slug":"an-empirical-comparison-of-lm-based-question","title":"An Empirical Comparison of LM-based Question and Answer Generation Methods","date":"2023-05-26","arxiv_id":"2305.17002","repositories_listed":1,"syntology":null},{"url":"/paper/an-investigation-of-noise-in-morphological","slug":"an-investigation-of-noise-in-morphological","title":"An Investigation of Noise in Morphological Inflection","date":"2023-05-26","arxiv_id":"2305.16581","repositories_listed":1,"syntology":null},{"url":"/paper/backpack-language-models","slug":"backpack-language-models","title":"Backpack Language Models","date":"2023-05-26","arxiv_id":"2305.16765","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":3,"n_ran_checked":3,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 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; 0 where Syntology's instrument failed) · 1 unverified; every one of the 3 samples that ran constructed an object rather than computing a result","sample_list":"/paper/backpack-language-models#ran","syntology_url":"https://syntology.ai/paper/2305.16765","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.16765"}},"official":null}},{"url":"/paper/datachat-prototyping-a-conversational-agent","slug":"datachat-prototyping-a-conversational-agent","title":"DataChat: Prototyping a Conversational Agent for Dataset Search and Visualization","date":"2023-05-26","arxiv_id":"2305.18358","repositories_listed":1,"syntology":null},{"url":"/paper/honey-i-shrunk-the-language-language-model","slug":"honey-i-shrunk-the-language-language-model","title":"Honey, I Shrunk the Language: Language Model Behavior at Reduced Scale","date":"2023-05-26","arxiv_id":"2305.17266","repositories_listed":1,"syntology":null},{"url":"/paper/leveraging-domain-knowledge-for-inclusive-and","slug":"leveraging-domain-knowledge-for-inclusive-and","title":"Leveraging Domain Knowledge for Inclusive and Bias-aware Humanitarian Response Entry Classification","date":"2023-05-26","arxiv_id":"2305.16756","repositories_listed":1,"syntology":null},{"url":"/paper/llms-and-the-abstraction-and-reasoning-corpus","slug":"llms-and-the-abstraction-and-reasoning-corpus","title":"LLMs and the Abstraction and Reasoning Corpus: Successes, Failures, and the Importance of Object-based Representations","date":"2023-05-26","arxiv_id":"2305.18354","repositories_listed":1,"syntology":null},{"url":"/paper/schema-guided-user-satisfaction-modeling-for","slug":"schema-guided-user-satisfaction-modeling-for","title":"Schema-Guided User Satisfaction Modeling for Task-Oriented Dialogues","date":"2023-05-26","arxiv_id":"2305.16798","repositories_listed":1,"syntology":null},{"url":"/paper/tokenization-impacts-multilingual-language","slug":"tokenization-impacts-multilingual-language","title":"Tokenization Impacts Multilingual Language Modeling: Assessing Vocabulary Allocation and Overlap Across Languages","date":"2023-05-26","arxiv_id":"2305.17179","repositories_listed":1,"syntology":null},{"url":"/paper/zero-shot-visual-question-answering-with","slug":"zero-shot-visual-question-answering-with","title":"Zero-shot Visual Question Answering with Language Model Feedback","date":"2023-05-26","arxiv_id":"2305.17006","repositories_listed":1,"syntology":null},{"url":"/paper/chatbridge-bridging-modalities-with-large","slug":"chatbridge-bridging-modalities-with-large","title":"ChatBridge: Bridging Modalities with Large Language Model as a Language Catalyst","date":"2023-05-25","arxiv_id":"2305.16103","repositories_listed":1,"syntology":{"n":9,"n_ran":7,"n_constructed":0,"n_ran_checked":1,"n_instrument":6,"n_unverified":2,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":1,"phrase":"7 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; 6 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/chatbridge-bridging-modalities-with-large#ran","syntology_url":"https://syntology.ai/paper/2305.16103","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.16103"}},"official":null}},{"url":"/paper/generatect-text-guided-3d-chest-ct-generation","slug":"generatect-text-guided-3d-chest-ct-generation","title":"GenerateCT: Text-Conditional Generation of 3D Chest CT Volumes","date":"2023-05-25","arxiv_id":"2305.16037","repositories_listed":1,"syntology":{"n":15,"n_ran":14,"n_constructed":0,"n_ran_checked":13,"n_instrument":1,"n_unverified":1,"n_honours":1,"n_violates":4,"n_no_contract":8,"n_pointer_only":5,"phrase":"14 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 1 honoured, 4 violated, 8 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/generatect-text-guided-3d-chest-ct-generation#ran","syntology_url":"https://syntology.ai/paper/2305.16037","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.16037"}},"official":{"repos":["ibrahimethemhamamci/generatect"],"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/language-models-implement-simple-word2vec","slug":"language-models-implement-simple-word2vec","title":"Language Models Implement Simple Word2Vec-style Vector Arithmetic","date":"2023-05-25","arxiv_id":"2305.16130","repositories_listed":1,"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/language-models-implement-simple-word2vec#ran","syntology_url":"https://syntology.ai/paper/2305.16130","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.16130"}},"official":{"repos":["jmerullo/lm_vector_arithmetic"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/masked-and-permuted-implicit-context-learning","slug":"masked-and-permuted-implicit-context-learning","title":"Masked and Permuted Implicit Context Learning for Scene Text Recognition","date":"2023-05-25","arxiv_id":"2305.16172","repositories_listed":1,"syntology":null},{"url":"/paper/rewritelm-an-instruction-tuned-large-language","slug":"rewritelm-an-instruction-tuned-large-language","title":"RewriteLM: An Instruction-Tuned Large Language Model for Text Rewriting","date":"2023-05-25","arxiv_id":"2305.15685","repositories_listed":1,"syntology":null},{"url":"/paper/the-false-promise-of-imitating-proprietary","slug":"the-false-promise-of-imitating-proprietary","title":"The False Promise of Imitating Proprietary LLMs","date":"2023-05-25","arxiv_id":"2305.15717","repositories_listed":1,"syntology":null},{"url":"/paper/2305-15017","slug":"2305-15017","title":"Calc-X and Calcformers: Empowering Arithmetical Chain-of-Thought through Interaction with Symbolic Systems","date":"2023-05-24","arxiv_id":"2305.15017","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":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) · 1 unverified","sample_list":"/paper/2305-15017#ran","syntology_url":"https://syntology.ai/paper/2305.15017","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.15017"}},"official":{"repos":["prompteus/calc-x"],"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/adapting-language-models-to-compress-contexts","slug":"adapting-language-models-to-compress-contexts","title":"Adapting Language Models to Compress Contexts","date":"2023-05-24","arxiv_id":"2305.14788","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":1,"n_ran_checked":1,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":2,"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) · 1 unverified; the one sample that ran constructed an object rather than computing a result","sample_list":"/paper/adapting-language-models-to-compress-contexts#ran","syntology_url":"https://syntology.ai/paper/2305.14788","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.14788"}},"official":{"repos":["princeton-nlp/autocompressors"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/an-efficient-multilingual-language-model","slug":"an-efficient-multilingual-language-model","title":"An Efficient Multilingual Language Model Compression through Vocabulary Trimming","date":"2023-05-24","arxiv_id":"2305.15020","repositories_listed":1,"syntology":{"n":9,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":0,"phrase":"6 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; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/an-efficient-multilingual-language-model#ran","syntology_url":"https://syntology.ai/paper/2305.15020","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.15020"}},"official":{"repos":["asahi417/lm-vocab-trimmer"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/beamsearchqa-large-language-models-are-strong","slug":"beamsearchqa-large-language-models-are-strong","title":"Allies: Prompting Large Language Model with Beam Search","date":"2023-05-24","arxiv_id":"2305.14766","repositories_listed":1,"syntology":{"n":13,"n_ran":5,"n_constructed":0,"n_ran_checked":4,"n_instrument":1,"n_unverified":8,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":2,"phrase":"5 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; 1 where Syntology's instrument failed) · 8 unverified","sample_list":"/paper/beamsearchqa-large-language-models-are-strong#ran","syntology_url":"https://syntology.ai/paper/2305.14766","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.14766"}},"official":{"repos":["microsoft/simxns"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":8,"ran_from_kinds":["official"]}}},{"url":"/paper/clusterllm-large-language-models-as-a-guide","slug":"clusterllm-large-language-models-as-a-guide","title":"ClusterLLM: Large Language Models as a Guide for Text Clustering","date":"2023-05-24","arxiv_id":"2305.14871","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":1,"n_honours":1,"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; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/clusterllm-large-language-models-as-a-guide#ran","syntology_url":"https://syntology.ai/paper/2305.14871","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.14871"}},"official":{"repos":["zhang-yu-wei/clusterllm"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/comsl-a-composite-speech-language-model-for-1","slug":"comsl-a-composite-speech-language-model-for-1","title":"ComSL: A Composite Speech-Language Model for End-to-End Speech-to-Text Translation","date":"2023-05-24","arxiv_id":"2305.14838","repositories_listed":1,"syntology":null},{"url":"/paper/csts-conditional-semantic-textual-similarity","slug":"csts-conditional-semantic-textual-similarity","title":"C-STS: Conditional Semantic Textual Similarity","date":"2023-05-24","arxiv_id":"2305.15093","repositories_listed":1,"syntology":{"n":4,"n_ran":2,"n_constructed":2,"n_ran_checked":2,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":4,"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) · 2 unverified; every one of the 2 samples that ran constructed an object rather than computing a result","sample_list":"/paper/csts-conditional-semantic-textual-similarity#ran","syntology_url":"https://syntology.ai/paper/2305.15093","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.15093"}},"official":{"repos":["princeton-nlp/c-sts"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/estimating-large-language-model-capabilities","slug":"estimating-large-language-model-capabilities","title":"Estimating Large Language Model Capabilities without Labeled Test Data","date":"2023-05-24","arxiv_id":"2305.14802","repositories_listed":1,"syntology":null},{"url":"/paper/gorilla-large-language-model-connected-with","slug":"gorilla-large-language-model-connected-with","title":"Gorilla: Large Language Model Connected with Massive APIs","date":"2023-05-24","arxiv_id":"2305.15334","repositories_listed":1,"syntology":null},{"url":"/paper/how-predictable-are-large-language-model","slug":"how-predictable-are-large-language-model","title":"How Predictable Are Large Language Model Capabilities? A Case Study on BIG-bench","date":"2023-05-24","arxiv_id":"2305.14947","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":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/how-predictable-are-large-language-model#ran","syntology_url":"https://syntology.ai/paper/2305.14947","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.14947"}},"official":{"repos":["ink-usc/predicting-big-bench"],"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/improving-language-models-with-advantage","slug":"improving-language-models-with-advantage","title":"Leftover Lunch: Advantage-based Offline Reinforcement Learning for Language Models","date":"2023-05-24","arxiv_id":"2305.14718","repositories_listed":1,"syntology":{"n":7,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":1,"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) · 4 unverified","sample_list":"/paper/improving-language-models-with-advantage#ran","syntology_url":"https://syntology.ai/paper/2305.14718","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.14718"}},"official":{"repos":["abaheti95/lol-rl"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/in-context-demonstration-selection-with-cross","slug":"in-context-demonstration-selection-with-cross","title":"In-Context Demonstration Selection with Cross Entropy Difference","date":"2023-05-24","arxiv_id":"2305.14726","repositories_listed":1,"syntology":null},{"url":"/paper/inference-time-policy-adapters-ipa-tailoring","slug":"inference-time-policy-adapters-ipa-tailoring","title":"Inference-Time Policy Adapters (IPA): Tailoring Extreme-Scale LMs without Fine-tuning","date":"2023-05-24","arxiv_id":"2305.15065","repositories_listed":1,"syntology":{"n":11,"n_ran":9,"n_constructed":3,"n_ran_checked":5,"n_instrument":4,"n_unverified":2,"n_honours":2,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"9 ran (of which 3 constructed an object rather than computing a result; 5 with no instrument failure: 2 honoured, 0 violated, 3 with no contract checked; 4 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/inference-time-policy-adapters-ipa-tailoring#ran","syntology_url":"https://syntology.ai/paper/2305.15065","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.15065"}},"official":{"repos":["gximinglu/ipa"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":3,"n_ran_no_instrument_failure":5,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/llmdet-a-large-language-models-detection-tool","slug":"llmdet-a-large-language-models-detection-tool","title":"LLMDet: A Third Party Large Language Models Generated Text Detection Tool","date":"2023-05-24","arxiv_id":"2305.15004","repositories_listed":1,"syntology":{"n":3,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":2,"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) · 2 unverified","sample_list":"/paper/llmdet-a-large-language-models-detection-tool#ran","syntology_url":"https://syntology.ai/paper/2305.15004","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.15004"}},"official":{"repos":["trustedllm/llmdet"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/meta-learning-online-adaptation-of-language","slug":"meta-learning-online-adaptation-of-language","title":"Meta-Learning Online Adaptation of Language Models","date":"2023-05-24","arxiv_id":"2305.15076","repositories_listed":1,"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":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) · 0 unverified","sample_list":"/paper/meta-learning-online-adaptation-of-language#ran","syntology_url":"https://syntology.ai/paper/2305.15076","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.15076"}},"official":{"repos":["nathanhu0/CaMeLS"],"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/pathasst-redefining-pathology-through","slug":"pathasst-redefining-pathology-through","title":"PathAsst: A Generative Foundation AI Assistant Towards Artificial General Intelligence of Pathology","date":"2023-05-24","arxiv_id":"2305.15072","repositories_listed":1,"syntology":null},{"url":"/paper/pivoine-instruction-tuning-for-open-world","slug":"pivoine-instruction-tuning-for-open-world","title":"PIVOINE: Instruction Tuning for Open-world Information Extraction","date":"2023-05-24","arxiv_id":"2305.14898","repositories_listed":1,"syntology":{"n":4,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":2,"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) · 2 unverified","sample_list":"/paper/pivoine-instruction-tuning-for-open-world#ran","syntology_url":"https://syntology.ai/paper/2305.14898","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.14898"}},"official":{"repos":["lukeming-tsinghua/instruction-tuning-for-open-world-ie"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/prompt-optimization-of-large-language-model","slug":"prompt-optimization-of-large-language-model","title":"AutoPlan: Automatic Planning of Interactive Decision-Making Tasks With Large Language Models","date":"2023-05-24","arxiv_id":"2305.15064","repositories_listed":1,"syntology":{"n":4,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":1,"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, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/prompt-optimization-of-large-language-model#ran","syntology_url":"https://syntology.ai/paper/2305.15064","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.15064"}},"official":{"repos":["owaski/autoplan"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/self-evolution-learning-for-discriminative","slug":"self-evolution-learning-for-discriminative","title":"Self-Evolution Learning for Discriminative Language Model Pretraining","date":"2023-05-24","arxiv_id":"2305.15275","repositories_listed":1,"syntology":null},{"url":"/paper/spring-gpt-4-out-performs-rl-algorithms-by","slug":"spring-gpt-4-out-performs-rl-algorithms-by","title":"SPRING: Studying the Paper and Reasoning to Play Games","date":"2023-05-24","arxiv_id":"2305.15486","repositories_listed":1,"syntology":null},{"url":"/paper/text-augmented-open-knowledge-graph","slug":"text-augmented-open-knowledge-graph","title":"Text-Augmented Open Knowledge Graph Completion via Pre-Trained Language Models","date":"2023-05-24","arxiv_id":"2305.15597","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":4,"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) · 1 unverified","sample_list":"/paper/text-augmented-open-knowledge-graph#ran","syntology_url":"https://syntology.ai/paper/2305.15597","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.15597"}},"official":{"repos":["pat-jj/tagreal"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/the-art-of-socratic-questioning-zero-shot","slug":"the-art-of-socratic-questioning-zero-shot","title":"The Art of SOCRATIC QUESTIONING: Recursive Thinking with Large Language Models","date":"2023-05-24","arxiv_id":"2305.14999","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":2,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"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) · 0 unverified; every one of the 2 samples that ran constructed an object rather than computing a result","sample_list":"/paper/the-art-of-socratic-questioning-zero-shot#ran","syntology_url":"https://syntology.ai/paper/2305.14999","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.14999"}},"official":{"repos":["vt-nlp/socratic-questioning"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/think-before-you-act-decision-transformers","slug":"think-before-you-act-decision-transformers","title":"Think Before You Act: Decision Transformers with Working Memory","date":"2023-05-24","arxiv_id":"2305.16338","repositories_listed":1,"syntology":{"n":12,"n_ran":7,"n_constructed":3,"n_ran_checked":5,"n_instrument":2,"n_unverified":5,"n_honours":2,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"7 ran (of which 3 constructed an object rather than computing a result; 5 with no instrument failure: 2 honoured, 0 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/think-before-you-act-decision-transformers#ran","syntology_url":"https://syntology.ai/paper/2305.16338","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.16338"}},"official":{"repos":["luciferkonn/dt_mem"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":3,"n_ran_no_instrument_failure":5,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/this-land-is-your-my-land-evaluating","slug":"this-land-is-your-my-land-evaluating","title":"This Land is {Your, My} Land: Evaluating Geopolitical Biases in Language Models","date":"2023-05-24","arxiv_id":"2305.14610","repositories_listed":1,"syntology":null},{"url":"/paper/towards-few-shot-entity-recognition-in-2","slug":"towards-few-shot-entity-recognition-in-2","title":"Towards Few-shot Entity Recognition in Document Images: A Graph Neural Network Approach Robust to Image Manipulation","date":"2023-05-24","arxiv_id":"2305.14828","repositories_listed":1,"syntology":null},{"url":"/paper/trade-offs-between-fairness-and-privacy-in","slug":"trade-offs-between-fairness-and-privacy-in","title":"Trade-Offs Between Fairness and Privacy in Language Modeling","date":"2023-05-24","arxiv_id":"2305.14936","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":1,"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; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/trade-offs-between-fairness-and-privacy-in#ran","syntology_url":"https://syntology.ai/paper/2305.14936","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.14936"}},"official":{"repos":["cleolotta/fair-and-private-lm"],"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","unlocated"]}}},{"url":"/paper/winner-take-all-column-row-sampling-for","slug":"winner-take-all-column-row-sampling-for","title":"Winner-Take-All Column Row Sampling for Memory Efficient Adaptation of Language Model","date":"2023-05-24","arxiv_id":"2305.15265","repositories_listed":1,"syntology":null},{"url":"/paper/2305-14585","slug":"2305-14585","title":"Faithful and Efficient Explanations for Neural Networks via Neural Tangent Kernel Surrogate Models","date":"2023-05-23","arxiv_id":"2305.14585","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":2,"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) · 1 unverified","sample_list":"/paper/2305-14585#ran","syntology_url":"https://syntology.ai/paper/2305.14585","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.14585"}},"official":{"repos":["pnnl/projection_ntk"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/a-simple-method-for-unsupervised-bilingual","slug":"a-simple-method-for-unsupervised-bilingual","title":"When your Cousin has the Right Connections: Unsupervised Bilingual Lexicon Induction for Related Data-Imbalanced Languages","date":"2023-05-23","arxiv_id":"2305.14012","repositories_listed":1,"syntology":null},{"url":"/paper/aligning-large-language-models-through","slug":"aligning-large-language-models-through","title":"Aligning Large Language Models through Synthetic Feedback","date":"2023-05-23","arxiv_id":"2305.13735","repositories_listed":1,"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":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) · 0 unverified; the one sample that ran constructed an object rather than computing a result","sample_list":"/paper/aligning-large-language-models-through#ran","syntology_url":"https://syntology.ai/paper/2305.13735","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.13735"}},"official":{"repos":["naver-ai/almost"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/appls-a-meta-evaluation-testbed-for-plain","slug":"appls-a-meta-evaluation-testbed-for-plain","title":"APPLS: Evaluating Evaluation Metrics for Plain Language Summarization","date":"2023-05-23","arxiv_id":"2305.14341","repositories_listed":1,"syntology":null},{"url":"/paper/automatic-model-selection-with-large-language","slug":"automatic-model-selection-with-large-language","title":"Automatic Model Selection with Large Language Models for Reasoning","date":"2023-05-23","arxiv_id":"2305.14333","repositories_listed":1,"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/automatic-model-selection-with-large-language#ran","syntology_url":"https://syntology.ai/paper/2305.14333","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.14333"}},"official":{"repos":["xuzhao0/model-selection-reasoning"],"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/axomiyaberta-a-phonologically-aware","slug":"axomiyaberta-a-phonologically-aware","title":"AxomiyaBERTa: A Phonologically-aware Transformer Model for Assamese","date":"2023-05-23","arxiv_id":"2305.13641","repositories_listed":1,"syntology":null},{"url":"/paper/clip4str-a-simple-baseline-for-scene-text-1","slug":"clip4str-a-simple-baseline-for-scene-text-1","title":"CLIP4STR: A Simple Baseline for Scene Text Recognition with Pre-trained Vision-Language Model","date":"2023-05-23","arxiv_id":"2305.14014","repositories_listed":1,"syntology":{"n":10,"n_ran":6,"n_constructed":0,"n_ran_checked":3,"n_instrument":3,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":2,"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) · 4 unverified","sample_list":"/paper/clip4str-a-simple-baseline-for-scene-text-1#ran","syntology_url":"https://syntology.ai/paper/2305.14014","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.14014"}},"official":null}},{"url":"/paper/congrat-self-supervised-contrastive","slug":"congrat-self-supervised-contrastive","title":"ConGraT: Self-Supervised Contrastive Pretraining for Joint Graph and Text Embeddings","date":"2023-05-23","arxiv_id":"2305.14321","repositories_listed":1,"syntology":null},{"url":"/paper/discrete-prompt-optimization-via-constrained","slug":"discrete-prompt-optimization-via-constrained","title":"Discrete Prompt Optimization via Constrained Generation for Zero-shot Re-ranker","date":"2023-05-23","arxiv_id":"2305.13729","repositories_listed":1,"syntology":null},{"url":"/paper/domain-private-transformers","slug":"domain-private-transformers","title":"Domain Private Transformers for Multi-Domain Dialog Systems","date":"2023-05-23","arxiv_id":"2305.14208","repositories_listed":1,"syntology":null},{"url":"/paper/error-detection-for-text-to-sql-semantic","slug":"error-detection-for-text-to-sql-semantic","title":"Error Detection for Text-to-SQL Semantic Parsing","date":"2023-05-23","arxiv_id":"2305.13683","repositories_listed":1,"syntology":null},{"url":"/paper/exploring-contrast-consistency-of-open-domain","slug":"exploring-contrast-consistency-of-open-domain","title":"Exploring Contrast Consistency of Open-Domain Question Answering Systems on Minimally Edited Questions","date":"2023-05-23","arxiv_id":"2305.14441","repositories_listed":1,"syntology":null},{"url":"/paper/goal-driven-explainable-clustering-via","slug":"goal-driven-explainable-clustering-via","title":"Goal-Driven Explainable Clustering via Language Descriptions","date":"2023-05-23","arxiv_id":"2305.13749","repositories_listed":1,"syntology":null},{"url":"/paper/images-in-language-space-exploring-the","slug":"images-in-language-space-exploring-the","title":"Images in Language Space: Exploring the Suitability of Large Language Models for Vision & Language Tasks","date":"2023-05-23","arxiv_id":"2305.13782","repositories_listed":1,"syntology":null},{"url":"/paper/improving-factuality-and-reasoning-in","slug":"improving-factuality-and-reasoning-in","title":"Improving Factuality and Reasoning in Language Models through Multiagent Debate","date":"2023-05-23","arxiv_id":"2305.14325","repositories_listed":1,"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/improving-factuality-and-reasoning-in#ran","syntology_url":"https://syntology.ai/paper/2305.14325","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.14325"}},"official":{"repos":["composable-models/llm_multiagent_debate"],"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/learn-from-mistakes-through-cooperative","slug":"learn-from-mistakes-through-cooperative","title":"Learning from Mistakes via Cooperative Study Assistant for Large Language Models","date":"2023-05-23","arxiv_id":"2305.13829","repositories_listed":1,"syntology":{"n":13,"n_ran":11,"n_constructed":0,"n_ran_checked":9,"n_instrument":2,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":0,"phrase":"11 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; 2 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/learn-from-mistakes-through-cooperative#ran","syntology_url":"https://syntology.ai/paper/2305.13829","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.13829"}},"official":{"repos":["dqwang122/salam"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":2,"ran_from_kinds":["found_in_text","official"]}}},{"url":"/paper/leveraging-open-information-extraction-for","slug":"leveraging-open-information-extraction-for","title":"Leveraging Open Information Extraction for More Robust Domain Transfer of Event Trigger Detection","date":"2023-05-23","arxiv_id":"2305.14163","repositories_listed":1,"syntology":null},{"url":"/paper/making-the-implicit-explicit-implicit-content","slug":"making-the-implicit-explicit-implicit-content","title":"Natural Language Decompositions of Implicit Content Enable Better Text Representations","date":"2023-05-23","arxiv_id":"2305.14583","repositories_listed":1,"syntology":null},{"url":"/paper/mathdial-a-dialogue-tutoring-dataset-with","slug":"mathdial-a-dialogue-tutoring-dataset-with","title":"MathDial: A Dialogue Tutoring Dataset with Rich Pedagogical Properties Grounded in Math Reasoning Problems","date":"2023-05-23","arxiv_id":"2305.14536","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":2,"n_instrument":2,"n_unverified":0,"n_honours":1,"n_violates":1,"n_no_contract":0,"n_pointer_only":4,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 1 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/mathdial-a-dialogue-tutoring-dataset-with#ran","syntology_url":"https://syntology.ai/paper/2305.14536","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.14536"}},"official":{"repos":["eth-nlped/mathdial"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/mitigating-language-model-hallucination-with","slug":"mitigating-language-model-hallucination-with","title":"The Knowledge Alignment Problem: Bridging Human and External Knowledge for Large Language Models","date":"2023-05-23","arxiv_id":"2305.13669","repositories_listed":1,"syntology":null},{"url":"/paper/mitigating-test-time-bias-for-fair-image-1","slug":"mitigating-test-time-bias-for-fair-image-1","title":"Mitigating Test-Time Bias for Fair Image Retrieval","date":"2023-05-23","arxiv_id":"2305.19329","repositories_listed":1,"syntology":null},{"url":"/paper/on-robustness-of-finetuned-transformer-based","slug":"on-robustness-of-finetuned-transformer-based","title":"On Robustness of Finetuned Transformer-based NLP Models","date":"2023-05-23","arxiv_id":"2305.14453","repositories_listed":1,"syntology":null},{"url":"/paper/parameter-efficient-language-model-tuning","slug":"parameter-efficient-language-model-tuning","title":"Parameter-Efficient Language Model Tuning with Active Learning in Low-Resource Settings","date":"2023-05-23","arxiv_id":"2305.14576","repositories_listed":1,"syntology":null},{"url":"/paper/preserving-knowledge-invariance-rethinking","slug":"preserving-knowledge-invariance-rethinking","title":"Preserving Knowledge Invariance: Rethinking Robustness Evaluation of Open Information Extraction","date":"2023-05-23","arxiv_id":"2305.13981","repositories_listed":1,"syntology":{"n":9,"n_ran":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":7,"n_pointer_only":1,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 1 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/preserving-knowledge-invariance-rethinking#ran","syntology_url":"https://syntology.ai/paper/2305.13981","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.13981"}},"official":{"repos":["qijimrc/robust"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/prompt-based-monte-carlo-tree-search-for-goal","slug":"prompt-based-monte-carlo-tree-search-for-goal","title":"Prompt-Based Monte-Carlo Tree Search for Goal-Oriented Dialogue Policy Planning","date":"2023-05-23","arxiv_id":"2305.13660","repositories_listed":1,"syntology":{"n":6,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":6,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":6,"phrase":"0 ran · 6 unverified","sample_list":"/paper/prompt-based-monte-carlo-tree-search-for-goal#ran","syntology_url":"https://syntology.ai/paper/2305.13660","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.13660"}},"official":{"repos":["jasonyux/gdpzero"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":6,"ran_from_kinds":[]}}},{"url":"/paper/visorgpt-learning-visual-prior-via-generative","slug":"visorgpt-learning-visual-prior-via-generative","title":"VisorGPT: Learning Visual Prior via Generative Pre-Training","date":"2023-05-23","arxiv_id":"2305.13777","repositories_listed":1,"syntology":null},{"url":"/paper/when-the-music-stops-tip-of-the-tongue","slug":"when-the-music-stops-tip-of-the-tongue","title":"When the Music Stops: Tip-of-the-Tongue Retrieval for Music","date":"2023-05-23","arxiv_id":"2305.14072","repositories_listed":1,"syntology":null},{"url":"/paper/wikichat-a-few-shot-llm-based-chatbot","slug":"wikichat-a-few-shot-llm-based-chatbot","title":"WikiChat: Stopping the Hallucination of Large Language Model Chatbots by Few-Shot Grounding on Wikipedia","date":"2023-05-23","arxiv_id":"2305.14292","repositories_listed":1,"syntology":{"n":7,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":2,"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) · 2 unverified","sample_list":"/paper/wikichat-a-few-shot-llm-based-chatbot#ran","syntology_url":"https://syntology.ai/paper/2305.14292","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.14292"}},"official":{"repos":["stanford-oval/wikichat"],"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/a-frustratingly-simple-decoding-method-for","slug":"a-frustratingly-simple-decoding-method-for","title":"A Frustratingly Simple Decoding Method for Neural Text Generation","date":"2023-05-22","arxiv_id":"2305.12675","repositories_listed":1,"syntology":null},{"url":"/paper/a-study-of-generative-large-language-model","slug":"a-study-of-generative-large-language-model","title":"A Study of Generative Large Language Model for Medical Research and Healthcare","date":"2023-05-22","arxiv_id":"2305.13523","repositories_listed":1,"syntology":null},{"url":"/paper/bidirectional-transformer-reranker-for","slug":"bidirectional-transformer-reranker-for","title":"Bidirectional Transformer Reranker for Grammatical Error Correction","date":"2023-05-22","arxiv_id":"2305.13000","repositories_listed":1,"syntology":null},{"url":"/paper/chain-of-knowledge-a-framework-for-grounding","slug":"chain-of-knowledge-a-framework-for-grounding","title":"Chain-of-Knowledge: Grounding Large Language Models via Dynamic Knowledge Adapting over Heterogeneous Sources","date":"2023-05-22","arxiv_id":"2305.13269","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":1,"n_no_contract":2,"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, 1 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/chain-of-knowledge-a-framework-for-grounding#ran","syntology_url":"https://syntology.ai/paper/2305.13269","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.13269"}},"official":{"repos":["damo-nlp-sg/chain-of-knowledge"],"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/conquer-contextualized-query-reduction-using","slug":"conquer-contextualized-query-reduction-using","title":"ConQueR: Contextualized Query Reduction using Search Logs","date":"2023-05-22","arxiv_id":"2305.12662","repositories_listed":1,"syntology":null},{"url":"/paper/distilling-chatgpt-for-explainable-automated","slug":"distilling-chatgpt-for-explainable-automated","title":"Distilling ChatGPT for Explainable Automated Student Answer Assessment","date":"2023-05-22","arxiv_id":"2305.12962","repositories_listed":1,"syntology":null},{"url":"/paper/farewell-to-aimless-large-scale-pretraining","slug":"farewell-to-aimless-large-scale-pretraining","title":"Farewell to Aimless Large-scale Pretraining: Influential Subset Selection for Language Model","date":"2023-05-22","arxiv_id":"2305.12816","repositories_listed":1,"syntology":null},{"url":"/paper/federated-learning-of-medical-concepts","slug":"federated-learning-of-medical-concepts","title":"Federated Learning of Medical Concepts Embedding using BEHRT","date":"2023-05-22","arxiv_id":"2305.13052","repositories_listed":1,"syntology":null},{"url":"/paper/how-language-model-hallucinations-can","slug":"how-language-model-hallucinations-can","title":"How Language Model Hallucinations Can Snowball","date":"2023-05-22","arxiv_id":"2305.13534","repositories_listed":1,"syntology":null},{"url":"/paper/lion-adversarial-distillation-of-closed","slug":"lion-adversarial-distillation-of-closed","title":"Lion: Adversarial Distillation of Proprietary Large Language Models","date":"2023-05-22","arxiv_id":"2305.12870","repositories_listed":1,"syntology":{"n":11,"n_ran":6,"n_constructed":0,"n_ran_checked":5,"n_instrument":1,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":1,"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) · 5 unverified","sample_list":"/paper/lion-adversarial-distillation-of-closed#ran","syntology_url":"https://syntology.ai/paper/2305.12870","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.12870"}},"official":{"repos":["yjiangcm/lion"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":5,"ran_from_kinds":["official"]}}}],"record_sha256":"756ce22a5d2cde080a9bde1785cd52a30a8aadc5f6804a8a5a9802a8a8ce087a","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}