{"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/9","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":9,"pages_in_order":20,"rows_per_page":100,"rows":[801,900],"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/8","next":"/task/natural-language-inference/papers/10","papers":[{"url":"/paper/social-bias-in-elicited-natural-language","slug":"social-bias-in-elicited-natural-language","title":"Social Bias in Elicited Natural Language Inferences","date":"2017-04-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/textual-entailment-with-structured-attentions","slug":"textual-entailment-with-structured-attentions","title":"Textual Entailment with Structured Attentions and Composition","date":"2017-01-04","arxiv_id":"1701.01126","repositories_listed":1,"syntology":null},{"url":"/paper/correcting-contradictions","slug":"correcting-contradictions","title":"Correcting Contradictions","date":"2017-01-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/textual-inference-getting-logic-from-humans","slug":"textual-inference-getting-logic-from-humans","title":"Textual Inference: getting logic from humans","date":"2017-01-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/building-a-dictionary-of-affixal-negations","slug":"building-a-dictionary-of-affixal-negations","title":"Building a Dictionary of Affixal Negations","date":"2016-12-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/building-compositional-semantics-and-higher","slug":"building-compositional-semantics-and-higher","title":"Building compositional semantics and higher-order inference system for a wide-coverage Japanese CCG parser","date":"2016-11-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/ccg2lambda-a-compositional-semantics-system","slug":"ccg2lambda-a-compositional-semantics-system","title":"ccg2lambda: A Compositional Semantics System","date":"2016-08-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/constructing-a-natural-language-inference","slug":"constructing-a-natural-language-inference","title":"Constructing a Natural Language Inference Dataset using Generative Neural Networks","date":"2016-07-20","arxiv_id":"1607.06025","repositories_listed":1,"syntology":null},{"url":"/paper/neural-tree-indexers-for-text-understanding","slug":"neural-tree-indexers-for-text-understanding","title":"Neural Tree Indexers for Text Understanding","date":"2016-07-15","arxiv_id":"1607.04492","repositories_listed":1,"syntology":null},{"url":"/paper/neural-associative-memory-for-dual-sequence","slug":"neural-associative-memory-for-dual-sequence","title":"Neural Associative Memory for Dual-Sequence Modeling","date":"2016-06-13","arxiv_id":"1606.03864","repositories_listed":1,"syntology":null},{"url":"/paper/knowledge-guided-linguistic-rewrites-for","slug":"knowledge-guided-linguistic-rewrites-for","title":"Knowledge-Guided Linguistic Rewrites for Inference Rule Verification","date":"2016-06-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/joint-learning-of-sentence-embeddings-for","slug":"joint-learning-of-sentence-embeddings-for","title":"Joint Learning of Sentence Embeddings for Relevance and Entailment","date":"2016-05-16","arxiv_id":"1605.04655","repositories_listed":1,"syntology":null},{"url":"/paper/sentence-pair-scoring-towards-unified","slug":"sentence-pair-scoring-towards-unified","title":"Sentence Pair Scoring: Towards Unified Framework for Text Comprehension","date":"2016-03-19","arxiv_id":"1603.06127","repositories_listed":1,"syntology":null},{"url":"/paper/discrete-state-variational-autoencoders-for","slug":"discrete-state-variational-autoencoders-for","title":"Discrete-State Variational Autoencoders for Joint Discovery and Factorization of Relations","date":"2016-01-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/idiom-paraphrases-seventh-heaven-vs-cloud","slug":"idiom-paraphrases-seventh-heaven-vs-cloud","title":"Idiom Paraphrases: Seventh Heaven vs Cloud Nine","date":"2015-09-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/ckylark-a-more-robust-pcfg-la-parser","slug":"ckylark-a-more-robust-pcfg-la-parser","title":"Ckylark: A More Robust PCFG-LA Parser","date":"2015-06-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/representing-meaning-with-a-combination-of","slug":"representing-meaning-with-a-combination-of","title":"Representing Meaning with a Combination of Logical and Distributional Models","date":"2015-05-26","arxiv_id":"1505.06816","repositories_listed":1,"syntology":null},{"url":"/paper/learning-to-distinguish-hypernyms-and-co","slug":"learning-to-distinguish-hypernyms-and-co","title":"Learning to Distinguish Hypernyms and Co-Hyponyms","date":"2014-08-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/uow-nlp-techniques-developed-at-the","slug":"uow-nlp-techniques-developed-at-the","title":"UoW: NLP techniques developed at the University of Wolverhampton for Semantic Similarity and Textual Entailment","date":"2014-08-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/a-random-walk-approach-to-selectional","slug":"a-random-walk-approach-to-selectional","title":"A Random Walk Approach to Selectional Preferences Based on Preference Ranking and Propagation","date":"2013-08-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/parma-a-predicate-argument-aligner","slug":"parma-a-predicate-argument-aligner","title":"PARMA: A Predicate Argument Aligner","date":"2013-08-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":null,"slug":"lrcti-a-large-language-model-based-framework","title":"LRCTI: A Large Language Model-Based Framework for Multi-Step Evidence Retrieval and Reasoning in Cyber Threat Intelligence Credibility Verification","date":"2025-07-15","arxiv_id":"2507.11310","repositories_listed":0,"syntology":null},{"url":null,"slug":"arag-agentic-retrieval-augmented-generation","title":"ARAG: Agentic Retrieval Augmented Generation for Personalized Recommendation","date":"2025-06-27","arxiv_id":"2506.21931","repositories_listed":0,"syntology":null},{"url":"/paper/thunder-nubench-a-benchmark-for-llms-sentence","slug":"thunder-nubench-a-benchmark-for-llms-sentence","title":"Thunder-NUBench: A Benchmark for LLMs' Sentence-Level Negation Understanding","date":"2025-06-17","arxiv_id":"2506.14397","repositories_listed":0,"syntology":null},{"url":null,"slug":"when-does-meaning-backfire-investigating-the","title":"When Does Meaning Backfire? Investigating the Role of AMRs in NLI","date":"2025-06-17","arxiv_id":"2506.14613","repositories_listed":0,"syntology":null},{"url":null,"slug":"2506-08713","title":"Explainable Compliance Detection with Multi-Hop Natural Language Inference on Assurance Case Structure","date":"2025-06-10","arxiv_id":"2506.08713","repositories_listed":0,"syntology":null},{"url":null,"slug":"clatter-comprehensive-entailment-reasoning","title":"CLATTER: Comprehensive Entailment Reasoning for Hallucination Detection","date":"2025-06-05","arxiv_id":"2506.05243","repositories_listed":0,"syntology":null},{"url":null,"slug":"faithful-and-robust-llm-driven-theorem","title":"Faithful and Robust LLM-Driven Theorem Proving for NLI Explanations","date":"2025-05-30","arxiv_id":"2505.24264","repositories_listed":0,"syntology":null},{"url":null,"slug":"gate-general-arabic-text-embedding-for","title":"GATE: General Arabic Text Embedding for Enhanced Semantic Textual Similarity with Matryoshka Representation Learning and Hybrid Loss Training","date":"2025-05-30","arxiv_id":"2505.24581","repositories_listed":0,"syntology":null},{"url":null,"slug":"preemptive-hallucination-reduction-an-input","title":"Preemptive Hallucination Reduction: An Input-Level Approach for Multimodal Language Model","date":"2025-05-29","arxiv_id":"2505.24007","repositories_listed":0,"syntology":null},{"url":null,"slug":"prismatic-synthesis-gradient-based-data","title":"Prismatic Synthesis: Gradient-based Data Diversification Boosts Generalization in LLM Reasoning","date":"2025-05-26","arxiv_id":"2505.20161","repositories_listed":0,"syntology":null},{"url":null,"slug":"s2lpp-small-to-large-prompt-prediction-across","title":"S2LPP: Small-to-Large Prompt Prediction across LLMs","date":"2025-05-26","arxiv_id":"2505.20097","repositories_listed":0,"syntology":null},{"url":null,"slug":"deftx-denoised-sparse-fine-tuning-for-zero","title":"DeFTX: Denoised Sparse Fine-Tuning for Zero-Shot Cross-Lingual Transfer","date":"2025-05-21","arxiv_id":"2505.15090","repositories_listed":0,"syntology":null},{"url":null,"slug":"2505-11470","title":"No Gold Standard, No Problem: Reference-Free Evaluation of Taxonomies","date":"2025-05-16","arxiv_id":"2505.11470","repositories_listed":0,"syntology":null},{"url":null,"slug":"boosting-neural-language-inference-via","title":"Boosting Neural Language Inference via Cascaded Interactive Reasoning","date":"2025-05-10","arxiv_id":"2505.06607","repositories_listed":0,"syntology":null},{"url":null,"slug":"document-attribution-examining-citation","title":"Document Attribution: Examining Citation Relationships using Large Language Models","date":"2025-05-09","arxiv_id":"2505.06324","repositories_listed":0,"syntology":null},{"url":null,"slug":"pushing-the-boundary-on-natural-language","title":"Pushing the boundary on Natural Language Inference","date":"2025-04-25","arxiv_id":"2504.18376","repositories_listed":0,"syntology":null},{"url":null,"slug":"grounded-in-context-retrieval-based-method","title":"Grounded in Context: Retrieval-Based Method for Hallucination Detection","date":"2025-04-22","arxiv_id":"2504.15771","repositories_listed":0,"syntology":null},{"url":null,"slug":"salad-improving-robustness-and-generalization","title":"SALAD: Improving Robustness and Generalization through Contrastive Learning with Structure-Aware and LLM-Driven Augmented Data","date":"2025-04-16","arxiv_id":"2504.12185","repositories_listed":0,"syntology":null},{"url":null,"slug":"cross-document-cross-lingual-natural-language","title":"Cross-Document Cross-Lingual NLI via RST-Enhanced Graph Fusion and Interpretability Prediction","date":"2025-04-11","arxiv_id":"2504.12324","repositories_listed":0,"syntology":null},{"url":null,"slug":"medhal-an-evaluation-dataset-for-medical","title":"MedHal: An Evaluation Dataset for Medical Hallucination Detection","date":"2025-04-11","arxiv_id":"2504.08596","repositories_listed":0,"syntology":null},{"url":null,"slug":"negation-a-pink-elephant-in-the-large","title":"Negation: A Pink Elephant in the Large Language Models' Room?","date":"2025-03-28","arxiv_id":"2503.22395","repositories_listed":0,"syntology":null},{"url":null,"slug":"hausanlp-at-semeval-2025-task-3-towards-a","title":"HausaNLP at SemEval-2025 Task 3: Towards a Fine-Grained Model-Aware Hallucination Detection","date":"2025-03-25","arxiv_id":"2503.19650","repositories_listed":0,"syntology":null},{"url":null,"slug":"collaboration-is-all-you-need-llm-assisted","title":"Collaboration is all you need: LLM Assisted Safe Code Translation","date":"2025-03-14","arxiv_id":"2503.11237","repositories_listed":0,"syntology":null},{"url":null,"slug":"introducing-verification-task-of-set","title":"Introducing Verification Task of Set Consistency with Set-Consistency Energy Networks","date":"2025-03-12","arxiv_id":"2503.10695","repositories_listed":0,"syntology":null},{"url":null,"slug":"esnlir-a-spanish-multi-genre-dataset-with","title":"ESNLIR: A Spanish Multi-Genre Dataset with Causal Relationships","date":"2025-03-11","arxiv_id":"2503.08803","repositories_listed":0,"syntology":null},{"url":null,"slug":"giving-ai-personalities-leads-to-more-human","title":"Giving AI Personalities Leads to More Human-Like Reasoning","date":"2025-02-19","arxiv_id":"2502.14155","repositories_listed":0,"syntology":null},{"url":null,"slug":"beyond-english-the-impact-of-prompt","title":"Beyond English: The Impact of Prompt Translation Strategies across Languages and Tasks in Multilingual LLMs","date":"2025-02-13","arxiv_id":"2502.09331","repositories_listed":0,"syntology":null},{"url":null,"slug":"morphnli-a-stepwise-approach-to-natural","title":"MorphNLI: A Stepwise Approach to Natural Language Inference Using Text Morphing","date":"2025-02-13","arxiv_id":"2502.09567","repositories_listed":0,"syntology":null},{"url":null,"slug":"neuro-symbolic-contrastive-learning-for-cross","title":"Neuro-Symbolic Contrastive Learning for Cross-domain Inference","date":"2025-02-13","arxiv_id":"2502.09213","repositories_listed":0,"syntology":null},{"url":null,"slug":"does-training-on-synthetic-data-make-models","title":"Does Training on Synthetic Data Make Models Less Robust?","date":"2025-02-11","arxiv_id":"2502.07164","repositories_listed":0,"syntology":null},{"url":null,"slug":"discourse-driven-evaluation-unveiling-factual","title":"Discourse-Driven Evaluation: Unveiling Factual Inconsistency in Long Document Summarization","date":"2025-02-10","arxiv_id":"2502.06185","repositories_listed":0,"syntology":null},{"url":null,"slug":"trustdatafilter-leveraging-trusted-knowledge","title":"TrustDataFilter:Leveraging Trusted Knowledge Base Data for More Effective Filtering of Unknown Information","date":"2025-01-25","arxiv_id":"2502.15714","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-study-of-the-plausibility-of-attention","title":"A Study of the Plausibility of Attention between RNN Encoders in Natural Language Inference","date":"2025-01-23","arxiv_id":"2501.13735","repositories_listed":0,"syntology":null},{"url":null,"slug":"academic-case-reports-lack-diversity","title":"Academic Case Reports Lack Diversity: Assessing the Presence and Diversity of Sociodemographic and Behavioral Factors related to Post COVID-19 Condition","date":"2025-01-21","arxiv_id":"2501.12538","repositories_listed":0,"syntology":null},{"url":null,"slug":"zero-shot-and-few-shot-learning-with","title":"Zero-shot and Few-shot Learning with Instruction-following LLMs for Claim Matching in Automated Fact-checking","date":"2025-01-18","arxiv_id":"2501.10860","repositories_listed":0,"syntology":null},{"url":null,"slug":"assessing-language-comprehension-in-large","title":"Assessing Language Comprehension in Large Language Models Using Construction Grammar","date":"2025-01-08","arxiv_id":"2501.04661","repositories_listed":0,"syntology":null},{"url":null,"slug":"from-superficial-patterns-to-semantic","title":"From Superficial Patterns to Semantic Understanding: Fine-Tuning Language Models on Contrast Sets","date":"2025-01-05","arxiv_id":"2501.02683","repositories_listed":0,"syntology":null},{"url":null,"slug":"hindillm-large-language-model-for-hindi","title":"HindiLLM: Large Language Model for Hindi","date":"2024-12-29","arxiv_id":"2412.20357","repositories_listed":0,"syntology":null},{"url":null,"slug":"in-context-learning-distillation-for","title":"In-Context Learning Distillation for Efficient Few-Shot Fine-Tuning","date":"2024-12-17","arxiv_id":"2412.13243","repositories_listed":0,"syntology":null},{"url":null,"slug":"explainable-procedural-mistake-detection","title":"Explainable Procedural Mistake Detection","date":"2024-12-16","arxiv_id":"2412.11927","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-head-attention-debiasing-and","title":"Multi-head attention debiasing and contrastive learning for mitigating Dataset Artifacts in Natural Language Inference","date":"2024-12-16","arxiv_id":"2412.16194","repositories_listed":0,"syntology":null},{"url":"/paper/first-train-to-generate-then-generate-to","slug":"first-train-to-generate-then-generate-to","title":"First Train to Generate, then Generate to Train: UnitedSynT5 for Few-Shot NLI","date":"2024-12-12","arxiv_id":"2412.09263","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-the-natural-language-inference","title":"Improving the Natural Language Inference robustness to hard dataset by data augmentation and preprocessing","date":"2024-12-10","arxiv_id":"2412.07108","repositories_listed":0,"syntology":null},{"url":null,"slug":"consolidating-and-developing-benchmarking","title":"Consolidating and Developing Benchmarking Datasets for the Nepali Natural Language Understanding Tasks","date":"2024-11-28","arxiv_id":"2411.19244","repositories_listed":0,"syntology":null},{"url":null,"slug":"lost-in-inference-rediscovering-the-role-of","title":"Lost in Inference: Rediscovering the Role of Natural Language Inference for Large Language Models","date":"2024-11-21","arxiv_id":"2411.14103","repositories_listed":0,"syntology":null},{"url":null,"slug":"patentedits-framing-patent-novelty-as-textual","title":"PatentEdits: Framing Patent Novelty as Textual Entailment","date":"2024-11-20","arxiv_id":"2411.13477","repositories_listed":0,"syntology":null},{"url":null,"slug":"transformer-based-contextualized-language","title":"Transformer-Based Contextualized Language Models Joint with Neural Networks for Natural Language Inference in Vietnamese","date":"2024-11-20","arxiv_id":"2411.13407","repositories_listed":0,"syntology":null},{"url":null,"slug":"beyond-keywords-a-context-based-hybrid","title":"Beyond Keywords: A Context-based Hybrid Approach to Mining Ethical Concern-related App Reviews","date":"2024-11-11","arxiv_id":"2411.07398","repositories_listed":0,"syntology":null},{"url":null,"slug":"gradual-fine-tuning-with-graph-routing-for","title":"Gradual Fine-Tuning with Graph Routing for Multi-Source Unsupervised Domain Adaptation","date":"2024-11-11","arxiv_id":"2411.07185","repositories_listed":0,"syntology":null},{"url":null,"slug":"explaining-mixtures-of-sources-in-news","title":"Explaining Mixtures of Sources in News Articles","date":"2024-11-07","arxiv_id":"2411.05192","repositories_listed":0,"syntology":null},{"url":null,"slug":"provenance-a-light-weight-fact-checker-for","title":"Provenance: A Light-weight Fact-checker for Retrieval Augmented LLM Generation Output","date":"2024-11-01","arxiv_id":"2411.01022","repositories_listed":0,"syntology":null},{"url":null,"slug":"teaching-a-language-model-to-distinguish","title":"Teaching a Language Model to Distinguish Between Similar Details using a Small Adversarial Training Set","date":"2024-10-30","arxiv_id":"2410.23118","repositories_listed":0,"syntology":null},{"url":null,"slug":"natural-language-inference-improves","title":"Natural Language Inference Improves Compositionality in Vision-Language Models","date":"2024-10-29","arxiv_id":"2410.22315","repositories_listed":0,"syntology":null},{"url":null,"slug":"relation-based-counterfactual-data","title":"Relation-based Counterfactual Data Augmentation and Contrastive Learning for Robustifying Natural Language Inference Models","date":"2024-10-28","arxiv_id":"2410.20710","repositories_listed":0,"syntology":null},{"url":null,"slug":"sg-fsm-a-self-guiding-zero-shot-prompting","title":"SG-FSM: A Self-Guiding Zero-Shot Prompting Paradigm for Multi-Hop Question Answering Based on Finite State Machine","date":"2024-10-22","arxiv_id":"2410.17021","repositories_listed":0,"syntology":null},{"url":null,"slug":"from-test-taking-to-test-making-examining-llm","title":"From Test-Taking to Test-Making: Examining LLM Authoring of Commonsense Assessment Items","date":"2024-10-18","arxiv_id":"2410.14897","repositories_listed":0,"syntology":null},{"url":null,"slug":"syllobio-nli-evaluating-large-language-models","title":"SylloBio-NLI: Evaluating Large Language Models on Biomedical Syllogistic Reasoning","date":"2024-10-18","arxiv_id":"2410.14399","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-a-scale-from-1-to-5-quantifying","title":"On A Scale From 1 to 5: Quantifying Hallucination in Faithfulness Evaluation","date":"2024-10-16","arxiv_id":"2410.12222","repositories_listed":0,"syntology":null},{"url":null,"slug":"alvin-active-learning-via-interpolation","title":"ALVIN: Active Learning Via INterpolation","date":"2024-10-11","arxiv_id":"2410.08972","repositories_listed":0,"syntology":null},{"url":null,"slug":"hypothesis-only-biases-in-large-language","title":"Hypothesis-only Biases in Large Language Model-Elicited Natural Language Inference","date":"2024-10-11","arxiv_id":"2410.08996","repositories_listed":0,"syntology":null},{"url":null,"slug":"measuring-the-groundedness-of-legal-question","title":"Measuring the Groundedness of Legal Question-Answering Systems","date":"2024-10-11","arxiv_id":"2410.08764","repositories_listed":0,"syntology":null},{"url":null,"slug":"publichearingbr-a-brazilian-portuguese","title":"PublicHearingBR: A Brazilian Portuguese Dataset of Public Hearing Transcripts for Summarization of Long Documents","date":"2024-10-10","arxiv_id":"2410.07495","repositories_listed":0,"syntology":null},{"url":null,"slug":"reasoning-with-natural-language-explanations","title":"Reasoning with Natural Language Explanations","date":"2024-10-05","arxiv_id":"2410.04148","repositories_listed":0,"syntology":null},{"url":null,"slug":"auto-gda-automatic-domain-adaptation-for","title":"Auto-GDA: Automatic Domain Adaptation for Efficient Grounding Verification in Retrieval Augmented Generation","date":"2024-10-04","arxiv_id":"2410.03461","repositories_listed":0,"syntology":null},{"url":null,"slug":"nl-eye-abductive-nli-for-images","title":"NL-Eye: Abductive NLI for Images","date":"2024-10-03","arxiv_id":"2410.02613","repositories_listed":0,"syntology":null},{"url":null,"slug":"how-entangled-is-factuality-and-deception-in","title":"How Entangled is Factuality and Deception in German?","date":"2024-09-30","arxiv_id":"2409.20165","repositories_listed":0,"syntology":null},{"url":null,"slug":"evaluation-of-openai-o1-opportunities-and","title":"Evaluation of OpenAI o1: Opportunities and Challenges of AGI","date":"2024-09-27","arxiv_id":"2409.18486","repositories_listed":0,"syntology":null},{"url":null,"slug":"axcel-automated-explainable-consistency","title":"AXCEL: Automated eXplainable Consistency Evaluation using LLMs","date":"2024-09-25","arxiv_id":"2409.16984","repositories_listed":0,"syntology":null},{"url":null,"slug":"using-similarity-to-evaluate-factual","title":"Using Similarity to Evaluate Factual Consistency in Summaries","date":"2024-09-23","arxiv_id":"2409.15090","repositories_listed":0,"syntology":null},{"url":null,"slug":"2409-14168","title":"Towards Building Efficient Sentence BERT Models using Layer Pruning","date":"2024-09-21","arxiv_id":"2409.14168","repositories_listed":0,"syntology":null},{"url":null,"slug":"enhancing-slm-via-chatgpt-and-dataset","title":"Enhancing SLM via ChatGPT and Dataset Augmentation","date":"2024-09-19","arxiv_id":"2409.12599","repositories_listed":0,"syntology":null},{"url":null,"slug":"political-debate-efficient-zero-shot-and-few","title":"Political DEBATE: Efficient Zero-shot and Few-shot Classifiers for Political Text","date":"2024-09-03","arxiv_id":"2409.02078","repositories_listed":0,"syntology":null},{"url":null,"slug":"crowd-calibrator-can-annotator-disagreement","title":"Crowd-Calibrator: Can Annotator Disagreement Inform Calibration in Subjective Tasks?","date":"2024-08-26","arxiv_id":"2408.14141","repositories_listed":0,"syntology":null},{"url":null,"slug":"instruction-finetuning-for-leaderboard","title":"Instruction Finetuning for Leaderboard Generation from Empirical AI Research","date":"2024-08-19","arxiv_id":"2408.10141","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-a-generative-approach-for-emotion","title":"Towards a Generative Approach for Emotion Detection and Reasoning","date":"2024-08-09","arxiv_id":"2408.04906","repositories_listed":0,"syntology":null},{"url":null,"slug":"explicating-the-implicit-argument-detection","title":"Explicating the Implicit: Argument Detection Beyond Sentence Boundaries","date":"2024-08-08","arxiv_id":"2408.04246","repositories_listed":0,"syntology":null},{"url":null,"slug":"2408-03018","title":"Integrating Controllable Motion Skills from Demonstrations","date":"2024-08-06","arxiv_id":"2408.03018","repositories_listed":0,"syntology":null},{"url":null,"slug":"2408-02237","title":"Do Large Language Models Speak All Languages Equally? A Comparative Study in Low-Resource Settings","date":"2024-08-05","arxiv_id":"2408.02237","repositories_listed":0,"syntology":null},{"url":null,"slug":"2408-01935","title":"Defining and Evaluating Decision and Composite Risk in Language Models Applied to Natural Language Inference","date":"2024-08-04","arxiv_id":"2408.01935","repositories_listed":0,"syntology":null}],"record_sha256":"b42a1e546c6c72be935ce78bdc594f5d4de31e4ee2a2b9159b31e558208cbe2f","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}