Cover Image

Agree, Disagree, Explain: Decomposing Human Label Variation in NLI through the Lens of Explanations

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Hong, Pingjun, Chen, Beiduo, Peng, Siyao, de Marneffe, Marie-Catherine, Roth, Benjamin, Plank, Barbara
Format:	Preprint
Published:	2025
Subjects:	Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

LiTEx: A Linguistic Taxonomy of Explanations for Understanding Within-Label Variation in Natural Language Inference
by: Hong, Pingjun, et al.
Published: (2025)

VariErr NLI: Separating Annotation Error from Human Label Variation
by: Weber-Genzel, Leon, et al.
Published: (2024)

A Rose by Any Other Name: LLM-Generated Explanations Are Good Proxies for Human Explanations to Collect Label Distributions on NLI
by: Chen, Beiduo, et al.
Published: (2024)

Human Label Variation as Stable Signal: Learning Annotator-Specific Explanation Behavior via Cross-Annotator Preference Optimization
by: Chen, Beiduo, et al.
Published: (2026)

"Seeing the Big through the Small": Can LLMs Approximate Human Judgment Distributions on NLI from a Few Explanations?
by: Chen, Beiduo, et al.
Published: (2024)

Threading the Needle: Reweaving Chain-of-Thought Reasoning to Explain Human Label Variation
by: Chen, Beiduo, et al.
Published: (2025)

EVADE: LLM-Based Explanation Generation and Validation for Error Detection in NLI
by: Zuo, Longfei, et al.
Published: (2025)

Disagreeing Rationales: Rethinking Classification and Explainability Evaluation in Hate Speech Detection
by: Muscato, Benedetta, et al.
Published: (2026)

Not All Explanations Simulate Equally: Comparing Verbalized Feature Attributions and Self-Generated Rationales
by: Hong, Pingjun, et al.
Published: (2026)

Do LLM Self-Explanations Help Users Predict Model Behavior? Evaluating Counterfactual Simulatability with Pragmatic Perturbations
by: Hong, Pingjun, et al.
Published: (2026)

Different Tastes of Entities: Investigating Human Label Variation in Named Entity Annotations
by: Peng, Siyao, et al.
Published: (2024)

Decoupling the Effect of Chain-of-Thought Reasoning: A Human Label Variation Perspective
by: Chen, Beiduo, et al.
Published: (2026)

When Annotators Agree but Labels Disagree: The Projection Problem in Stance Detection
by: Zhang, Bowen
Published: (2026)

Agree to Disagree? A Meta-Evaluation of LLM Misgendering
by: Subramonian, Arjun, et al.
Published: (2025)

Reasoning that Travels: Dissecting How Chain-of-Thought Transfers Across Models
by: Cheng, Xinyuan, et al.
Published: (2026)

MAKIEval: A Multilingual Automatic WiKidata-based Framework for Cultural Awareness Evaluation for LLMs
by: Zhao, Raoyuan, et al.
Published: (2025)

CLIMATELI: Evaluating Entity Linking on Climate Change Data
by: Zhou, Shijia, et al.
Published: (2024)

Interpreting Predictive Probabilities: Model Confidence or Human Label Variation?
by: Baan, Joris, et al.
Published: (2024)

Evaluating Large Language Models for Cross-Lingual Retrieval
by: Zuo, Longfei, et al.
Published: (2025)

MaiBaam Annotation Guidelines
by: Blaschke, Verena, et al.
Published: (2024)

From Noise to Signal to Selbstzweck: Reframing Human Label Variation in the Era of Post-training in NLP
by: Xu, Shanshan, et al.
Published: (2025)

References Matter: Investigating the Impact of Reference Set Variation on Summarization Evaluation
by: Casola, Silvia, et al.
Published: (2025)

Explanation sensitivity to the randomness of large language models: the case of journalistic text classification
by: Bogaert, Jeremie, et al.
Published: (2024)

Revisiting Active Learning under (Human) Label Variation
by: Gruber, Cornelia, et al.
Published: (2025)

BoN Appetit Team at LeWiDi-2025: Best-of-N Test-time Scaling Can Not Stomach Annotation Disagreements (Yet)
by: Ruiz, Tomas, et al.
Published: (2025)

MaiBaam: A Multi-Dialectal Bavarian Universal Dependency Treebank
by: Blaschke, Verena, et al.
Published: (2024)

Humans and LLMs Diverge on Probabilistic Inferences
by: Kamath, Gaurav, et al.
Published: (2026)

MultiClimate: Multimodal Stance Detection on Climate Change Videos
by: Wang, Jiawen, et al.
Published: (2024)

Agree to Agree
Published: (2020)

Information Asymmetry across Language Varieties: A Case Study on Cantonese-Mandarin and Bavarian-German QA
by: Pei, Renhao, et al.
Published: (2026)

Sebastian, Basti, Wastl?! Recognizing Named Entities in Bavarian Dialectal Data
by: Peng, Siyao, et al.
Published: (2024)

EEVEE: An Easy Annotation Tool for Natural Language Processing
by: Sorensen, Axel, et al.
Published: (2024)

Explanation Regularisation through the Lens of Attributions
by: Ferreira, Pedro, et al.
Published: (2024)

Neural Text Normalization for Luxembourgish using Real-Life Variation Data
by: Lutgen, Anne-Marie, et al.
Published: (2024)

A survey of diversity quantification in natural language processing: The why, what, where and how
by: Estève, Louis, et al.
Published: (2025)

Variation is the Norm: Embracing Sociolinguistics in NLP
by: Lutgen, Anne-Marie, et al.
Published: (2026)

Faithful and Robust LLM-Driven Theorem Proving for NLI Explanations
by: Quan, Xin, et al.
Published: (2025)

Agree to Disagree: Measuring Hidden Dissent in FOMC Meetings
by: Tsang, Kwok Ping, et al.
Published: (2023)

Agree to Disagree: Consensus-Free Flocking under Constraints
by: Jardine, Peter Travis, et al.
Published: (2026)

Legal Experts Disagree With Rationale Extraction Techniques for Explaining ECtHR Case Outcome Classification
by: Namazov, Mahammad, et al.
Published: (2026)