{"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/natural-language-inference/papers/4","list_of":"/task/natural-language-inference","task":"Natural Language Inference","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":4,"pages_in_order":20,"rows_per_page":100,"rows":[301,400],"of":1961,"counts":{"archive_papers_tagged":1961,"with_a_code_link":821,"where_syntology_ran_a_sample":209,"not_listed_spam_title":0,"listed":1961,"listed_where_code_ran":209,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":170,"every_run_a_failure_of_syntologys_instrument":39,"listed_with_a_run_with_no_instrument_failure":170,"listed_every_run_a_failure_of_syntologys_instrument":39,"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/natural-language-inference","prev":"/task/natural-language-inference/papers/3","next":"/task/natural-language-inference/papers/5","papers":[{"url":"/paper/heuristics-driven-link-of-analogy-prompting","slug":"heuristics-driven-link-of-analogy-prompting","title":"LLMs Learn Task Heuristics from Demonstrations: A Heuristic-Driven Prompting Strategy for Document-Level Event Argument Extraction","date":"2023-11-11","arxiv_id":"2311.06555","repositories_listed":1,"syntology":{"n":6,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":6,"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) · 1 unverified","sample_list":"/paper/heuristics-driven-link-of-analogy-prompting#ran","syntology_url":"https://syntology.ai/paper/2311.06555","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.06555"}},"official":{"repos":["hzzhou01/hd-loa-prompting"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/deep-natural-language-feature-learning-for","slug":"deep-natural-language-feature-learning-for","title":"Deep Natural Language Feature Learning for Interpretable Prediction","date":"2023-11-09","arxiv_id":"2311.05754","repositories_listed":1,"syntology":null},{"url":"/paper/pragmatic-reasoning-unlocks-quantifier","slug":"pragmatic-reasoning-unlocks-quantifier","title":"Pragmatic Reasoning Unlocks Quantifier Semantics for Foundation Models","date":"2023-11-08","arxiv_id":"2311.04659","repositories_listed":1,"syntology":null},{"url":"/paper/promptcblue-a-chinese-prompt-tuning-benchmark","slug":"promptcblue-a-chinese-prompt-tuning-benchmark","title":"PromptCBLUE: A Chinese Prompt Tuning Benchmark for the Medical Domain","date":"2023-10-22","arxiv_id":"2310.14151","repositories_listed":1,"syntology":null},{"url":"/paper/ecologically-valid-explanations-for-label","slug":"ecologically-valid-explanations-for-label","title":"Ecologically Valid Explanations for Label Variation in NLI","date":"2023-10-20","arxiv_id":"2310.13850","repositories_listed":1,"syntology":null},{"url":"/paper/explaining-interactions-between-text-spans","slug":"explaining-interactions-between-text-spans","title":"Explaining Interactions Between Text Spans","date":"2023-10-20","arxiv_id":"2310.13506","repositories_listed":1,"syntology":null},{"url":"/paper/fast-and-accurate-factual-inconsistency","slug":"fast-and-accurate-factual-inconsistency","title":"Fast and Accurate Factual Inconsistency Detection Over Long Documents","date":"2023-10-19","arxiv_id":"2310.13189","repositories_listed":1,"syntology":{"n":9,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":7,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":9,"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) · 7 unverified","sample_list":"/paper/fast-and-accurate-factual-inconsistency#ran","syntology_url":"https://syntology.ai/paper/2310.13189","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.13189"}},"official":{"repos":["asappresearch/scale-score"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":7,"ran_from_kinds":["official"]}}},{"url":"/paper/investigating-semantic-subspaces-of","slug":"investigating-semantic-subspaces-of","title":"Investigating semantic subspaces of Transformer sentence embeddings through linear structural probing","date":"2023-10-18","arxiv_id":"2310.11923","repositories_listed":1,"syntology":null},{"url":"/paper/semantic-aware-contrastive-sentence","slug":"semantic-aware-contrastive-sentence","title":"Large Language Models can Contrastively Refine their Generation for Better Sentence Representation Learning","date":"2023-10-17","arxiv_id":"2310.10962","repositories_listed":1,"syntology":null},{"url":"/paper/chain-of-natural-language-inference-for","slug":"chain-of-natural-language-inference-for","title":"Chain of Natural Language Inference for Reducing Large Language Model Ungrounded Hallucinations","date":"2023-10-06","arxiv_id":"2310.03951","repositories_listed":1,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":0,"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) · 0 unverified","sample_list":"/paper/chain-of-natural-language-inference-for#ran","syntology_url":"https://syntology.ai/paper/2310.03951","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.03951"}},"official":{"repos":["microsoft/conli_hallucination"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/augmenting-transformers-with-recursively","slug":"augmenting-transformers-with-recursively","title":"Augmenting Transformers with Recursively Composed Multi-grained Representations","date":"2023-09-28","arxiv_id":"2309.16319","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":2,"n_ran_checked":2,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"3 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; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/augmenting-transformers-with-recursively#ran","syntology_url":"https://syntology.ai/paper/2309.16319","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.16319"}},"official":{"repos":["ant-research/structuredlm_rtdt"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/substituting-data-annotation-with-balanced","slug":"substituting-data-annotation-with-balanced","title":"Substituting Data Annotation with Balanced Updates and Collective Loss in Multi-label Text Classification","date":"2023-09-24","arxiv_id":"2309.13543","repositories_listed":1,"syntology":null},{"url":"/paper/evaluating-gender-bias-of-pre-trained","slug":"evaluating-gender-bias-of-pre-trained","title":"Evaluating Gender Bias of Pre-trained Language Models in Natural Language Inference by Considering All Labels","date":"2023-09-18","arxiv_id":"2309.09697","repositories_listed":1,"syntology":null},{"url":"/paper/splitee-early-exit-in-deep-neural-networks","slug":"splitee-early-exit-in-deep-neural-networks","title":"SplitEE: Early Exit in Deep Neural Networks with Split Computing","date":"2023-09-17","arxiv_id":"2309.09195","repositories_listed":1,"syntology":null},{"url":"/paper/x-parade-cross-lingual-textual-entailment-and","slug":"x-parade-cross-lingual-textual-entailment-and","title":"X-PARADE: Cross-Lingual Textual Entailment and Information Divergence across Paragraphs","date":"2023-09-16","arxiv_id":"2309.08873","repositories_listed":1,"syntology":null},{"url":"/paper/self-consistent-narrative-prompts-on","slug":"self-consistent-narrative-prompts-on","title":"Self-Consistent Narrative Prompts on Abductive Natural Language Inference","date":"2023-09-15","arxiv_id":"2309.08303","repositories_listed":1,"syntology":null},{"url":"/paper/oyxoy-a-modern-nlp-test-suite-for-modern","slug":"oyxoy-a-modern-nlp-test-suite-for-modern","title":"OYXOY: A Modern NLP Test Suite for Modern Greek","date":"2023-09-13","arxiv_id":"2309.07009","repositories_listed":1,"syntology":null},{"url":"/paper/batchprompt-accomplish-more-with-less","slug":"batchprompt-accomplish-more-with-less","title":"BatchPrompt: Accomplish more with less","date":"2023-09-01","arxiv_id":"2309.00384","repositories_listed":1,"syntology":null},{"url":"/paper/link-prediction-for-wikipedia-articles-as-a","slug":"link-prediction-for-wikipedia-articles-as-a","title":"Link Prediction for Wikipedia Articles as a Natural Language Inference Task","date":"2023-08-31","arxiv_id":"2308.16469","repositories_listed":1,"syntology":null},{"url":"/paper/calm-a-multi-task-benchmark-for-comprehensive","slug":"calm-a-multi-task-benchmark-for-comprehensive","title":"CALM : A Multi-task Benchmark for Comprehensive Assessment of Language Model Bias","date":"2023-08-24","arxiv_id":"2308.12539","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":2,"n_no_contract":0,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 2 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/calm-a-multi-task-benchmark-for-comprehensive#ran","syntology_url":"https://syntology.ai/paper/2308.12539","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.12539"}},"official":{"repos":["vipulgupta1011/calm"],"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/lightweight-adaptation-of-neural-language","slug":"lightweight-adaptation-of-neural-language","title":"Lightweight Adaptation of Neural Language Models via Subspace Embedding","date":"2023-08-16","arxiv_id":"2308.08688","repositories_listed":1,"syntology":null},{"url":"/paper/synthesizing-political-zero-shot-relation","slug":"synthesizing-political-zero-shot-relation","title":"Leveraging Codebook Knowledge with NLI and ChatGPT for Zero-Shot Political Relation Classification","date":"2023-08-15","arxiv_id":"2308.07876","repositories_listed":1,"syntology":null},{"url":"/paper/do-multilingual-language-models-think-better","slug":"do-multilingual-language-models-think-better","title":"Do Multilingual Language Models Think Better in English?","date":"2023-08-02","arxiv_id":"2308.01223","repositories_listed":1,"syntology":{"n":3,"n_ran":1,"n_constructed":0,"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 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) · 2 unverified","sample_list":"/paper/do-multilingual-language-models-think-better#ran","syntology_url":"https://syntology.ai/paper/2308.01223","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.01223"}},"official":{"repos":["juletx/self-translate"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/improving-natural-language-inference-in","slug":"improving-natural-language-inference-in","title":"Improving Natural Language Inference in Arabic using Transformer Models and Linguistically Informed Pre-Training","date":"2023-07-27","arxiv_id":"2307.14666","repositories_listed":1,"syntology":null},{"url":"/paper/pac-neural-prediction-set-learning-to","slug":"pac-neural-prediction-set-learning-to","title":"Selective Generation for Controllable Language Models","date":"2023-07-18","arxiv_id":"2307.09254","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":5,"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/pac-neural-prediction-set-learning-to#ran","syntology_url":"https://syntology.ai/paper/2307.09254","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.09254"}},"official":{"repos":["ml-postech/selective-generation"],"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/is-prompt-based-finetuning-always-better-than","slug":"is-prompt-based-finetuning-always-better-than","title":"Is Prompt-Based Finetuning Always Better than Vanilla Finetuning? Insights from Cross-Lingual Language Understanding","date":"2023-07-15","arxiv_id":"2307.07880","repositories_listed":1,"syntology":null},{"url":"/paper/synthetic-dataset-for-evaluating-complex","slug":"synthetic-dataset-for-evaluating-complex","title":"Synthetic Dataset for Evaluating Complex Compositional Knowledge for Natural Language Inference","date":"2023-07-11","arxiv_id":"2307.05034","repositories_listed":1,"syntology":null},{"url":"/paper/lea-improving-sentence-similarity-robustness","slug":"lea-improving-sentence-similarity-robustness","title":"LEA: Improving Sentence Similarity Robustness to Typos Using Lexical Attention Bias","date":"2023-07-06","arxiv_id":"2307.02912","repositories_listed":1,"syntology":null},{"url":"/paper/spacenli-evaluating-the-consistency-of","slug":"spacenli-evaluating-the-consistency-of","title":"SpaceNLI: Evaluating the Consistency of Predicting Inferences in Space","date":"2023-07-05","arxiv_id":"2307.02269","repositories_listed":1,"syntology":null},{"url":"/paper/modeling-hierarchical-reasoning-chains-by-1","slug":"modeling-hierarchical-reasoning-chains-by-1","title":"Modeling Hierarchical Reasoning Chains by Linking Discourse Units and Key Phrases for Reading Comprehension","date":"2023-06-21","arxiv_id":"2306.12069","repositories_listed":1,"syntology":null},{"url":"/paper/jamp-controlled-japanese-temporal-inference","slug":"jamp-controlled-japanese-temporal-inference","title":"Jamp: Controlled Japanese Temporal Inference Dataset for Evaluating Generalization Capacity of Language Models","date":"2023-06-19","arxiv_id":"2306.10727","repositories_listed":1,"syntology":null},{"url":"/paper/neural-models-for-factual-inconsistency","slug":"neural-models-for-factual-inconsistency","title":"Neural models for Factual Inconsistency Classification with Explanations","date":"2023-06-15","arxiv_id":"2306.08872","repositories_listed":1,"syntology":null},{"url":"/paper/can-current-nli-systems-handle-german-word","slug":"can-current-nli-systems-handle-german-word","title":"Can current NLI systems handle German word order? Investigating language model performance on a new German challenge set of minimal pairs","date":"2023-06-07","arxiv_id":"2306.04523","repositories_listed":1,"syntology":null},{"url":"/paper/promptbench-towards-evaluating-the-robustness","slug":"promptbench-towards-evaluating-the-robustness","title":"PromptRobust: Towards Evaluating the Robustness of Large Language Models on Adversarial Prompts","date":"2023-06-07","arxiv_id":"2306.04528","repositories_listed":1,"syntology":null},{"url":"/paper/cue-an-uncertainty-interpretation-framework","slug":"cue-an-uncertainty-interpretation-framework","title":"CUE: An Uncertainty Interpretation Framework for Text Classifiers Built on Pre-Trained Language Models","date":"2023-06-06","arxiv_id":"2306.03598","repositories_listed":1,"syntology":null},{"url":"/paper/evaluating-the-effectiveness-of-natural","slug":"evaluating-the-effectiveness-of-natural","title":"Evaluating the Effectiveness of Natural Language Inference for Hate Speech Detection in Languages with Limited Labeled Data","date":"2023-06-06","arxiv_id":"2306.03722","repositories_listed":1,"syntology":null},{"url":"/paper/from-key-points-to-key-point-hierarchy","slug":"from-key-points-to-key-point-hierarchy","title":"From Key Points to Key Point Hierarchy: Structured and Expressive Opinion Summarization","date":"2023-06-06","arxiv_id":"2306.03853","repositories_listed":1,"syntology":{"n":9,"n_ran":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":0,"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) · 1 unverified","sample_list":"/paper/from-key-points-to-key-point-hierarchy#ran","syntology_url":"https://syntology.ai/paper/2306.03853","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.03853"}},"official":{"repos":["ibm/kpa-hierarchy"],"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/logiqa-2-0-an-improved-dataset-for-logical","slug":"logiqa-2-0-an-improved-dataset-for-logical","title":"LogiQA 2.0—An Improved Dataset for Logical Reasoning in Natural Language Understanding","date":"2023-06-06","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/a-study-of-situational-reasoning-for-traffic","slug":"a-study-of-situational-reasoning-for-traffic","title":"A Study of Situational Reasoning for Traffic Understanding","date":"2023-06-05","arxiv_id":"2306.02520","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":2,"n_instrument":3,"n_unverified":0,"n_honours":2,"n_violates":0,"n_no_contract":0,"n_pointer_only":5,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/a-study-of-situational-reasoning-for-traffic#ran","syntology_url":"https://syntology.ai/paper/2306.02520","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.02520"}},"official":{"repos":["saccharomycetes/text-based-traffic-understanding"],"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","unlocated"]}}},{"url":"/paper/thifly-research-at-semeval-2023-task-7-a","slug":"thifly-research-at-semeval-2023-task-7-a","title":"THiFLY Research at SemEval-2023 Task 7: A Multi-granularity System for CTR-based Textual Entailment and Evidence Retrieval","date":"2023-06-02","arxiv_id":"2306.01245","repositories_listed":1,"syntology":null},{"url":"/paper/amr4nli-interpretable-and-robust-nli-measures","slug":"amr4nli-interpretable-and-robust-nli-measures","title":"AMR4NLI: Interpretable and robust NLI measures from semantic graphs","date":"2023-06-01","arxiv_id":"2306.00936","repositories_listed":1,"syntology":null},{"url":"/paper/assessing-word-importance-using-models","slug":"assessing-word-importance-using-models","title":"Assessing Word Importance Using Models Trained for Semantic Tasks","date":"2023-05-31","arxiv_id":"2305.19689","repositories_listed":1,"syntology":null},{"url":"/paper/a-systematic-study-and-comprehensive","slug":"a-systematic-study-and-comprehensive","title":"A Systematic Study and Comprehensive Evaluation of ChatGPT on Benchmark Datasets","date":"2023-05-29","arxiv_id":"2305.18486","repositories_listed":1,"syntology":null},{"url":"/paper/lm-cppf-paraphrasing-guided-data-augmentation","slug":"lm-cppf-paraphrasing-guided-data-augmentation","title":"LM-CPPF: Paraphrasing-Guided Data Augmentation for Contrastive Prompt-Based Few-Shot Fine-Tuning","date":"2023-05-29","arxiv_id":"2305.18169","repositories_listed":1,"syntology":null},{"url":"/paper/biomedgpt-a-unified-and-generalist-biomedical","slug":"biomedgpt-a-unified-and-generalist-biomedical","title":"BiomedGPT: A Generalist Vision-Language Foundation Model for Diverse Biomedical Tasks","date":"2023-05-26","arxiv_id":"2305.17100","repositories_listed":1,"syntology":{"n":8,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":5,"n_pointer_only":7,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/biomedgpt-a-unified-and-generalist-biomedical#ran","syntology_url":"https://syntology.ai/paper/2305.17100","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.17100"}},"official":{"repos":["taokz/biomedgpt"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/characterizing-and-measuring-linguistic","slug":"characterizing-and-measuring-linguistic","title":"Characterizing and Measuring Linguistic Dataset Drift","date":"2023-05-26","arxiv_id":"2305.17127","repositories_listed":1,"syntology":null},{"url":"/paper/can-large-language-models-infer-and-disagree","slug":"can-large-language-models-infer-and-disagree","title":"Can Large Language Models Capture Dissenting Human Voices?","date":"2023-05-23","arxiv_id":"2305.13788","repositories_listed":1,"syntology":{"n":28,"n_ran":24,"n_constructed":0,"n_ran_checked":24,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":1,"n_no_contract":23,"n_pointer_only":0,"phrase":"24 ran (of which 0 constructed an object rather than computing a result; 24 with no instrument failure: 0 honoured, 1 violated, 23 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/can-large-language-models-infer-and-disagree#ran","syntology_url":"https://syntology.ai/paper/2305.13788","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.13788"}},"official":{"repos":["xfactlab/emnlp2023-llm-disagreement"],"state":"official (archive's flag): 14 ran","n_ran":14,"n_constructed":0,"n_ran_no_instrument_failure":14,"n_unverified":4,"ran_from_kinds":["found_in_text","official"]}}},{"url":"/paper/sociocultural-norm-similarities-and","slug":"sociocultural-norm-similarities-and","title":"Sociocultural Norm Similarities and Differences via Situational Alignment and Explainable Textual Entailment","date":"2023-05-23","arxiv_id":"2305.14492","repositories_listed":1,"syntology":null},{"url":"/paper/sources-of-hallucination-by-large-language","slug":"sources-of-hallucination-by-large-language","title":"Sources of Hallucination by Large Language Models on Inference Tasks","date":"2023-05-23","arxiv_id":"2305.14552","repositories_listed":1,"syntology":null},{"url":"/paper/enhancing-cross-lingual-natural-language-1","slug":"enhancing-cross-lingual-natural-language-1","title":"Enhancing Cross-lingual Natural Language Inference by Soft Prompting with Multilingual Verbalizer","date":"2023-05-22","arxiv_id":"2305.12761","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":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) · 1 unverified","sample_list":"/paper/enhancing-cross-lingual-natural-language-1#ran","syntology_url":"https://syntology.ai/paper/2305.12761","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.12761"}},"official":{"repos":["thu-bpm/softmv"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/logical-reasoning-for-natural-language","slug":"logical-reasoning-for-natural-language","title":"Atomic Inference for NLI with Generated Facts as Atoms","date":"2023-05-22","arxiv_id":"2305.13214","repositories_listed":1,"syntology":null},{"url":"/paper/refind-relation-extraction-financial-dataset","slug":"refind-relation-extraction-financial-dataset","title":"REFinD: Relation Extraction Financial Dataset","date":"2023-05-22","arxiv_id":"2305.18322","repositories_listed":1,"syntology":null},{"url":"/paper/sentence-representations-via-gaussian","slug":"sentence-representations-via-gaussian","title":"Sentence Representations via Gaussian Embedding","date":"2023-05-22","arxiv_id":"2305.12990","repositories_listed":1,"syntology":null},{"url":"/paper/contrastive-learning-with-logic-driven-data","slug":"contrastive-learning-with-logic-driven-data","title":"Abstract Meaning Representation-Based Logic-Driven Data Augmentation for Logical Reasoning","date":"2023-05-21","arxiv_id":"2305.12599","repositories_listed":1,"syntology":null},{"url":"/paper/from-alignment-to-entailment-a-unified","slug":"from-alignment-to-entailment-a-unified","title":"From Alignment to Entailment: A Unified Textual Entailment Framework for Entity Alignment","date":"2023-05-19","arxiv_id":"2305.11501","repositories_listed":1,"syntology":null},{"url":"/paper/solving-nlp-problems-through-human-system","slug":"solving-nlp-problems-through-human-system","title":"Solving NLP Problems through Human-System Collaboration: A Discussion-based Approach","date":"2023-05-19","arxiv_id":"2305.11789","repositories_listed":1,"syntology":null},{"url":"/paper/palm-2-technical-report-1","slug":"palm-2-technical-report-1","title":"PaLM 2 Technical Report","date":"2023-05-17","arxiv_id":"2305.10403","repositories_listed":1,"syntology":null},{"url":"/paper/scene-self-labeled-counterfactuals-for","slug":"scene-self-labeled-counterfactuals-for","title":"SCENE: Self-Labeled Counterfactuals for Extrapolating to Negative Examples","date":"2023-05-13","arxiv_id":"2305.07984","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":3,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/scene-self-labeled-counterfactuals-for#ran","syntology_url":"https://syntology.ai/paper/2305.07984","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.07984"}},"official":{"repos":["deqingfu/scene"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/zara-improving-few-shot-self-rationalization","slug":"zara-improving-few-shot-self-rationalization","title":"ZARA: Improving Few-Shot Self-Rationalization for Small Language Models","date":"2023-05-12","arxiv_id":"2305.07355","repositories_listed":1,"syntology":null},{"url":"/paper/automatic-evaluation-of-attribution-by-large","slug":"automatic-evaluation-of-attribution-by-large","title":"Automatic Evaluation of Attribution by Large Language Models","date":"2023-05-10","arxiv_id":"2305.06311","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/automatic-evaluation-of-attribution-by-large#ran","syntology_url":"https://syntology.ai/paper/2305.06311","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.06311"}},"official":{"repos":["osu-nlp-group/attrscore"],"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/mot-pre-thinking-and-recalling-enable-chatgpt","slug":"mot-pre-thinking-and-recalling-enable-chatgpt","title":"MoT: Memory-of-Thought Enables ChatGPT to Self-Improve","date":"2023-05-09","arxiv_id":"2305.05181","repositories_listed":1,"syntology":null},{"url":"/paper/stance-detection-with-supervised-zero-shot","slug":"stance-detection-with-supervised-zero-shot","title":"Stance Detection: A Practical Guide to Classifying Political Beliefs in Text","date":"2023-05-02","arxiv_id":"2305.01723","repositories_listed":1,"syntology":null},{"url":"/paper/pouf-prompt-oriented-unsupervised-fine-tuning","slug":"pouf-prompt-oriented-unsupervised-fine-tuning","title":"POUF: Prompt-oriented unsupervised fine-tuning for large pre-trained models","date":"2023-04-29","arxiv_id":"2305.00350","repositories_listed":1,"syntology":{"n":9,"n_ran":4,"n_constructed":0,"n_ran_checked":0,"n_instrument":4,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":9,"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) · 5 unverified","sample_list":"/paper/pouf-prompt-oriented-unsupervised-fine-tuning#ran","syntology_url":"https://syntology.ai/paper/2305.00350","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.00350"}},"official":{"repos":["korawat-tanwisuth/pouf"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/lamini-lm-a-diverse-herd-of-distilled-models","slug":"lamini-lm-a-diverse-herd-of-distilled-models","title":"LaMini-LM: A Diverse Herd of Distilled Models from Large-Scale Instructions","date":"2023-04-27","arxiv_id":"2304.14402","repositories_listed":1,"syntology":null},{"url":"/paper/sebis-at-semeval-2023-task-7-a-joint-system","slug":"sebis-at-semeval-2023-task-7-a-joint-system","title":"Sebis at SemEval-2023 Task 7: A Joint System for Natural Language Inference and Evidence Retrieval from Clinical Trial Reports","date":"2023-04-25","arxiv_id":"2304.13180","repositories_listed":1,"syntology":null},{"url":"/paper/receval-evaluating-reasoning-chains-via","slug":"receval-evaluating-reasoning-chains-via","title":"ReCEval: Evaluating Reasoning Chains via Correctness and Informativeness","date":"2023-04-21","arxiv_id":"2304.10703","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":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) · 1 unverified","sample_list":"/paper/receval-evaluating-reasoning-chains-via#ran","syntology_url":"https://syntology.ai/paper/2304.10703","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2304.10703"}},"official":{"repos":["archiki/receval"],"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/uncertainty-aware-natural-language-inference","slug":"uncertainty-aware-natural-language-inference","title":"Uncertainty-Aware Natural Language Inference with Stochastic Weight Averaging","date":"2023-04-10","arxiv_id":"2304.04726","repositories_listed":1,"syntology":{"n":6,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":4,"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) · 4 unverified","sample_list":"/paper/uncertainty-aware-natural-language-inference#ran","syntology_url":"https://syntology.ai/paper/2304.04726","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2304.04726"}},"official":{"repos":["helsinki-nlp/uncertainty-aware-nli"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/are-large-language-models-ready-for","slug":"are-large-language-models-ready-for","title":"Are Large Language Models Ready for Healthcare? A Comparative Study on Clinical Language Understanding","date":"2023-04-09","arxiv_id":"2304.05368","repositories_listed":1,"syntology":null},{"url":"/paper/evaluating-the-logical-reasoning-ability-of","slug":"evaluating-the-logical-reasoning-ability-of","title":"Evaluating the Logical Reasoning Ability of ChatGPT and GPT-4","date":"2023-04-07","arxiv_id":"2304.03439","repositories_listed":1,"syntology":null},{"url":"/paper/unsupervised-improvement-of-factual-knowledge","slug":"unsupervised-improvement-of-factual-knowledge","title":"Unsupervised Improvement of Factual Knowledge in Language Models","date":"2023-04-04","arxiv_id":"2304.01597","repositories_listed":1,"syntology":null},{"url":"/paper/a-multiple-choices-reading-comprehension","slug":"a-multiple-choices-reading-comprehension","title":"A Multiple Choices Reading Comprehension Corpus for Vietnamese Language Education","date":"2023-03-31","arxiv_id":"2303.18162","repositories_listed":1,"syntology":null},{"url":"/paper/nature-language-reasoning-a-survey","slug":"nature-language-reasoning-a-survey","title":"Natural Language Reasoning, A Survey","date":"2023-03-26","arxiv_id":"2303.14725","repositories_listed":1,"syntology":null},{"url":"/paper/logic-against-bias-textual-entailment","slug":"logic-against-bias-textual-entailment","title":"Logic Against Bias: Textual Entailment Mitigates Stereotypical Sentence Reasoning","date":"2023-03-10","arxiv_id":"2303.05670","repositories_listed":1,"syntology":null},{"url":"/paper/chatgpt-jack-of-all-trades-master-of-none","slug":"chatgpt-jack-of-all-trades-master-of-none","title":"ChatGPT: Jack of all trades, master of none","date":"2023-02-21","arxiv_id":"2302.10724","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/chatgpt-jack-of-all-trades-master-of-none#ran","syntology_url":"https://syntology.ai/paper/2302.10724","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.10724"}},"official":{"repos":["clarin-pl/chatgpt-evaluation-01-2023"],"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/keep-it-neutral-using-natural-language","slug":"keep-it-neutral-using-natural-language","title":"For Generated Text, Is NLI-Neutral Text the Best Text?","date":"2023-02-16","arxiv_id":"2302.08577","repositories_listed":1,"syntology":null},{"url":"/paper/investigating-multi-source-active-learning","slug":"investigating-multi-source-active-learning","title":"Investigating Multi-source Active Learning for Natural Language Inference","date":"2023-02-14","arxiv_id":"2302.06976","repositories_listed":1,"syntology":null},{"url":"/paper/language-model-analysis-for-ontology","slug":"language-model-analysis-for-ontology","title":"Language Model Analysis for Ontology Subsumption Inference","date":"2023-02-14","arxiv_id":"2302.06761","repositories_listed":1,"syntology":null},{"url":"/paper/compositional-exemplars-for-in-context","slug":"compositional-exemplars-for-in-context","title":"Compositional Exemplars for In-context Learning","date":"2023-02-11","arxiv_id":"2302.05698","repositories_listed":1,"syntology":{"n":7,"n_ran":5,"n_constructed":1,"n_ran_checked":2,"n_instrument":3,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"phrase":"5 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/compositional-exemplars-for-in-context#ran","syntology_url":"https://syntology.ai/paper/2302.05698","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.05698"}},"official":{"repos":["hkunlp/icl-ceil"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":1,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/evaluating-the-robustness-of-discrete-prompts","slug":"evaluating-the-robustness-of-discrete-prompts","title":"Evaluating the Robustness of Discrete Prompts","date":"2023-02-11","arxiv_id":"2302.05619","repositories_listed":1,"syntology":null},{"url":"/paper/explanation-selection-using-unlabeled-data","slug":"explanation-selection-using-unlabeled-data","title":"Explanation Selection Using Unlabeled Data for Chain-of-Thought Prompting","date":"2023-02-09","arxiv_id":"2302.04813","repositories_listed":1,"syntology":null},{"url":"/paper/lightweight-transformers-for-clinical-natural","slug":"lightweight-transformers-for-clinical-natural","title":"Lightweight Transformers for Clinical Natural Language Processing","date":"2023-02-09","arxiv_id":"2302.04725","repositories_listed":1,"syntology":null},{"url":"/paper/udapter-efficient-domain-adaptation-using","slug":"udapter-efficient-domain-adaptation-using","title":"UDApter -- Efficient Domain Adaptation Using Adapters","date":"2023-02-07","arxiv_id":"2302.03194","repositories_listed":1,"syntology":null},{"url":"/paper/guide-the-learner-controlling-product-of","slug":"guide-the-learner-controlling-product-of","title":"Guide the Learner: Controlling Product of Experts Debiasing Method Based on Token Attribution Similarities","date":"2023-02-06","arxiv_id":"2302.02852","repositories_listed":1,"syntology":null},{"url":"/paper/schema-guided-semantic-accuracy-faithfulness","slug":"schema-guided-semantic-accuracy-faithfulness","title":"Schema-Guided Semantic Accuracy: Faithfulness in Task-Oriented Dialogue Response Generation","date":"2023-01-29","arxiv_id":"2301.12568","repositories_listed":1,"syntology":null},{"url":"/paper/a-comparative-study-of-pretrained-language-1","slug":"a-comparative-study-of-pretrained-language-1","title":"A Comparative Study of Pretrained Language Models for Long Clinical Text","date":"2023-01-27","arxiv_id":"2301.11847","repositories_listed":1,"syntology":null},{"url":"/paper/swing-balancing-coverage-and-faithfulness-for","slug":"swing-balancing-coverage-and-faithfulness-for","title":"SWING: Balancing Coverage and Faithfulness for Dialogue Summarization","date":"2023-01-25","arxiv_id":"2301.10483","repositories_listed":1,"syntology":null},{"url":"/paper/opt-iml-scaling-language-model-instruction","slug":"opt-iml-scaling-language-model-instruction","title":"OPT-IML: Scaling Language Model Instruction Meta Learning through the Lens of Generalization","date":"2022-12-22","arxiv_id":"2212.12017","repositories_listed":1,"syntology":null},{"url":"/paper/can-nli-provide-proper-indirect-supervision","slug":"can-nli-provide-proper-indirect-supervision","title":"Can NLI Provide Proper Indirect Supervision for Low-resource Biomedical Relation Extraction?","date":"2022-12-21","arxiv_id":"2212.10784","repositories_listed":1,"syntology":null},{"url":"/paper/disco-distilling-phrasal-counterfactuals-with","slug":"disco-distilling-phrasal-counterfactuals-with","title":"DISCO: Distilling Counterfactuals with Large Language Models","date":"2022-12-20","arxiv_id":"2212.10534","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/disco-distilling-phrasal-counterfactuals-with#ran","syntology_url":"https://syntology.ai/paper/2212.10534","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.10534"}},"official":{"repos":["eric11eca/disco"],"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/wecheck-strong-factual-consistency-checker","slug":"wecheck-strong-factual-consistency-checker","title":"WeCheck: Strong Factual Consistency Checker via Weakly Supervised Learning","date":"2022-12-20","arxiv_id":"2212.10057","repositories_listed":1,"syntology":null},{"url":"/paper/cross-lingual-retrieval-augmented-prompt-for","slug":"cross-lingual-retrieval-augmented-prompt-for","title":"Cross-Lingual Retrieval Augmented Prompt for Low-Resource Languages","date":"2022-12-19","arxiv_id":"2212.09651","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":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) · 4 unverified","sample_list":"/paper/cross-lingual-retrieval-augmented-prompt-for#ran","syntology_url":"https://syntology.ai/paper/2212.09651","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.09651"}},"official":{"repos":["ercong21/parc"],"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/hype-better-pre-trained-language-model-fine","slug":"hype-better-pre-trained-language-model-fine","title":"HyPe: Better Pre-trained Language Model Fine-tuning with Hidden Representation Perturbation","date":"2022-12-17","arxiv_id":"2212.08853","repositories_listed":1,"syntology":null},{"url":"/paper/rpn-a-word-vector-level-data-augmentation","slug":"rpn-a-word-vector-level-data-augmentation","title":"RPN: A Word Vector Level Data Augmentation Algorithm in Deep Learning for Language Understanding","date":"2022-12-12","arxiv_id":"2212.05961","repositories_listed":1,"syntology":null},{"url":"/paper/lawngnli-a-long-premise-benchmark-for-in","slug":"lawngnli-a-long-premise-benchmark-for-in","title":"LawngNLI: A Long-Premise Benchmark for In-Domain Generalization from Short to Long Contexts and for Implication-Based Retrieval","date":"2022-12-06","arxiv_id":"2212.03222","repositories_listed":1,"syntology":null},{"url":"/paper/utilizing-background-knowledge-for-robust","slug":"utilizing-background-knowledge-for-robust","title":"Utilizing Background Knowledge for Robust Reasoning over Traffic Situations","date":"2022-12-04","arxiv_id":"2212.07798","repositories_listed":1,"syntology":null},{"url":"/paper/learning-to-select-from-multiple-options","slug":"learning-to-select-from-multiple-options","title":"Learning to Select from Multiple Options","date":"2022-12-01","arxiv_id":"2212.00301","repositories_listed":1,"syntology":null},{"url":"/paper/using-focal-loss-to-fight-shallow-heuristics","slug":"using-focal-loss-to-fight-shallow-heuristics","title":"Using Focal Loss to Fight Shallow Heuristics: An Empirical Analysis of Modulated Cross-Entropy in Natural Language Inference","date":"2022-11-23","arxiv_id":"2211.13331","repositories_listed":1,"syntology":null},{"url":"/paper/tempera-test-time-prompting-via-reinforcement","slug":"tempera-test-time-prompting-via-reinforcement","title":"TEMPERA: Test-Time Prompting via Reinforcement Learning","date":"2022-11-21","arxiv_id":"2211.11890","repositories_listed":1,"syntology":null},{"url":"/paper/looking-at-the-overlooked-an-analysis-on-the","slug":"looking-at-the-overlooked-an-analysis-on-the","title":"Looking at the Overlooked: An Analysis on the Word-Overlap Bias in Natural Language Inference","date":"2022-11-07","arxiv_id":"2211.03862","repositories_listed":1,"syntology":null},{"url":"/paper/learning-to-infer-from-unlabeled-data-a-semi","slug":"learning-to-infer-from-unlabeled-data-a-semi","title":"Learning to Infer from Unlabeled Data: A Semi-supervised Learning Approach for Robust Natural Language Inference","date":"2022-11-05","arxiv_id":"2211.02971","repositories_listed":1,"syntology":null}],"record_sha256":"2a0e384ff6c8b17102434a3f0b93b053d54bd0f0a2c76a511ca0cda4f5475746","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}