Natural Language Inference

Also known as NLI

Natural language inference (NLI) asks whether one text entails, contradicts, or leaves undetermined a claim in another, supporting tasks such as fact checking, argument analysis, and document review. Common approaches fine-tune transformer models or prompt large language models, while linguistic features, semantic graphs, and neuro-symbolic methods aim to make the reasoning more structured and interpretable. Benchmarks range from general-purpose datasets to adversarial, multilingual, clinical, and legal settings, with diagnostics probing phenomena such as negation, lexical changes, and implicit premises. A central challenge is that high benchmark scores can coexist with reliance on dataset artifacts, sensitivity to wording, and gaps between model judgments and human interpretations; annotation ambiguity and benchmark quality also complicate evaluation.

Latest papers

40 papers4 papers in the last four weeks, down 60% on the four weeks before. 0.0% of all new papers.

Fine-Grained Perspectives: Modeling Explanations with Annotator-Specific Rationales
Apr 23, 2026Olufunke O. Sarumi, Charles Welch, Daniel BraunAnnotator Disagreement Natural Language Inference
Marburg University, Marburg, Germany · McMaster University, Hamilton, Ontario, Canada
Product-of-Experts Training Reduces Dataset Artifacts in Natural Language Inference
Apr 21, 2026Aby Mammen MathewDebiased ML Natural Language Inference
The University of Texas at Austin
Comparing Human and Large Language Model Interpretation of Implicit Information
Apr 18, 2026Antonio De Santis, Tommaso Bonetti, Andrea Tocchetti +1Implicit Reasoning in Language Models LLM Information Extraction
Politecnico di Milano, Italy
Multi-Granularity Reasoning for Natural Language Inference
Apr 18, 2026Chunling Xi, Di LiangHierarchical Representation Learning Natural Language Inference
1Pacific Insurance Technology Co., Ltd. · 2Lixin Information Services (Shenzhen) Co., Ltd.
When Informal Text Breaks NLI: Tokenization Failure, Distribution Shift, and Targeted Mitigations
Apr 18, 2026Avinash Goutham AluguvellyDistribution Shift Language Model Robustness
University of Texas at Austin · Austin, TX, USA
Making Implicit Premises Explicit in Logical Understanding of Enthymemes
Mar 6, 2026Xuyao Feng, Anthony HunterNatural Language Inference Implicit Reasoning in Language Models
Department of Computer Science, University College London, United Kingdom
The Imperfective Paradox in Large Language Models
Jan 14, 2026Bolei Ma, Yusuke MiyaoFaithfulness of Language Model Reasoning Language Model Reasoning Evaluation
LMU Munich & MCML · The University of Tokyo
MERGE: Minimal Expression-Replacement GEneralization Test for Natural Language Inference
Oct 28, 2025Mădălina Zgreabăn, Tejaswini Deoskar, Lasha AbzianidzeLanguage Model Robustness Natural Language Inference
Utrecht Institute of Linguistics OTS, Utrecht University, The Netherlands
Evaluating the Scalability and Adversarial Generalization of GRPO-Trained NLI Models
Apr 25, 2025Pablo Miralles-González, Javier Huertas-Tato, Alejandro Martín +1LLM Fine-Tuning RL for Language Model Reasoning
Department of Computer Systems, Technical University of Madrid, Madrid, Spain · United Arab Emirates University, Al Ain, United Arab Emirates
Identification of Entailment and Contradiction Relations for Natural Language Argumentation: A Neurosymbolic Approach
May 2, 2024Xuyao Feng, Anthony HunterBoolean Satisfiability Natural Language Inference
Department of Computer Science, University College London, London, UK

Apr 23, 2026J/K move · Enter open · S save

Fine-Grained Perspectives: Modeling Explanations with Annotator-Specific Rationales

Olufunke O. Sarumi, Charles Welch, Daniel Braun

Marburg University, Marburg, Germany · McMaster University, Hamilton, Ontario, Canada

Annotator Disagreement Natural Language Inference

Open paper AskPDF arXiv

Beyond exploring disaggregated labels for modeling perspectives, annotator rationales provide fine-grained signals of individual perspectives. In this work, we propose a framework for jointly modeling annotator-specific label prediction and corresponding explanations, fine-tuned on the annotators' provided rationales. Using a dataset with disaggregated natural language inference (NLI) annotations and annotator-provided explanations, we condition predictions on both annotator identity and demographic metadata through a representation-level User Passport mechanism. We further introduce two explainer architectures: a post-hoc prompt-based explainer and a prefixed bridge explainer that transfers annotator-conditioned classifier representations directly into a generative model. This design enables explanation generation aligned with individual annotator perspectives. Our results show that incorporating explanation modeling substantially improves predictive performance over a baseline annotator-aware classifier, with the prefixed bridge approach achieving more stable label alignment and higher semantic consistency, while the post-hoc approach yields stronger lexical similarity. These findings indicate that modeling explanations as expressions of fine-grained perspective provides a richer and more faithful representation of disagreement. The proposed approaches advance perspectivist modeling by integrating annotator-specific rationales into both predictive and generative components.