Copertina

When Answers Stray from Questions: Hallucination Detection via Question-Answer Orthogonal Decomposition

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Yao, Siyang, Feng, Erhu, Xia, Yubin
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Machine Learning Artificial Intelligence Computation and Language
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

MultiQ&A: An Analysis in Measuring Robustness via Automated Crowdsourcing of Question Perturbations and Answers
di: Cho, Nicole, et al.
Pubblicazione: (2025)

Measuring and Reducing LLM Hallucination without Gold-Standard Answers
di: Wei, Jiaheng, et al.
Pubblicazione: (2024)

Anchored Answers: Unravelling Positional Bias in GPT-2's Multiple-Choice Questions
di: Li, Ruizhe, et al.
Pubblicazione: (2024)

The Challenge of Achieving Attributability in Multilingual Table-to-Text Generation with Question-Answer Blueprints
di: Haussmann, Aden
Pubblicazione: (2025)

Explicit Diversity Conditions for Effective Question Answer Generation with Large Language Models
di: Yadav, Vikas, et al.
Pubblicazione: (2024)

Multilingual Non-Factoid Question Answering with Answer Paragraph Selection
di: Mishra, Ritwik, et al.
Pubblicazione: (2024)

MeDiSumQA: Patient-Oriented Question-Answer Generation from Discharge Letters
di: Dada, Amin, et al.
Pubblicazione: (2025)

AQUA-Bench: Beyond Finding Answers to Knowing When There Are None in Audio Question Answering
di: Kuan, Chun-Yi, et al.
Pubblicazione: (2026)

Hallucination-Free Automatic Question & Answer Generation for Intuitive Learning
di: Wang, Nicholas X., et al.
Pubblicazione: (2026)

Rewarding Intellectual Humility Learning When Not To Answer In Large Language Models
di: Jha, Abha, et al.
Pubblicazione: (2026)

DefAn: Definitive Answer Dataset for LLMs Hallucination Evaluation
di: Rahman, A B M Ashikur, et al.
Pubblicazione: (2024)

Verif.ai: Towards an Open-Source Scientific Generative Question-Answering System with Referenced and Verifiable Answers
di: Košprdić, Miloš, et al.
Pubblicazione: (2024)

When Does a Language Model Commit? A Finite-Answer Theory of Pre-Verbalization Commitment
di: Zhang, Long, et al.
Pubblicazione: (2026)

Answer, Assemble, Ace: Understanding How LMs Answer Multiple Choice Questions
di: Wiegreffe, Sarah, et al.
Pubblicazione: (2024)

No Answer Needed: Predicting LLM Answer Accuracy from Question-Only Linear Probes
di: Cencerrado, Iván Vicente Moreno, et al.
Pubblicazione: (2025)

From Answers to Questions: EQGBench for Evaluating LLMs' Educational Question Generation
di: Zhou, Chengliang, et al.
Pubblicazione: (2025)

Proving that Cryptic Crossword Clue Answers are Correct
di: Andrews, Martin, et al.
Pubblicazione: (2024)

ExpertQA: Expert-Curated Questions and Attributed Answers
di: Malaviya, Chaitanya, et al.
Pubblicazione: (2023)

The Strongest Teacher Is Not Always the Best Teacher: Student-Centric Answer Selection
di: Hu, Zhengyu, et al.
Pubblicazione: (2026)

General Table Question Answering via Answer-Formula Joint Generation
di: Wang, Zhongyuan, et al.
Pubblicazione: (2025)

Graph Guided Question Answer Generation for Procedural Question-Answering
di: Pham, Hai X., et al.
Pubblicazione: (2024)

Augmenting Math Word Problems via Iterative Question Composing
di: Liu, Haoxiong, et al.
Pubblicazione: (2024)

Clarify, Abstain or Answer? Strategising in Conversation with Belief-Augmented Generation
di: Baan, Joris, et al.
Pubblicazione: (2026)

Question Answering with LLMs and Learning from Answer Sets
di: Borroto, Manuel, et al.
Pubblicazione: (2025)

Answer Matching Outperforms Multiple Choice for Language Model Evaluation
di: Chandak, Nikhil, et al.
Pubblicazione: (2025)

SelfReflect: Can LLMs Communicate Their Internal Answer Distribution?
di: Kirchhof, Michael, et al.
Pubblicazione: (2025)

ASAG2024: A Combined Benchmark for Short Answer Grading
di: Meyer, Gérôme, et al.
Pubblicazione: (2024)

When Single Answer Is Not Enough: Rethinking Single-Step Retrosynthesis Benchmarks for LLMs
di: Zagribelnyy, Bogdan, et al.
Pubblicazione: (2026)

Retrieval Augmented Question Answering: When Should LLMs Admit Ignorance?
di: Wang, Dingmin, et al.
Pubblicazione: (2025)

Putting People in LLMs' Shoes: Generating Better Answers via Question Rewriter
di: Chen, Junhao, et al.
Pubblicazione: (2024)

Inference-Time Intervention: Eliciting Truthful Answers from a Language Model
di: Li, Kenneth, et al.
Pubblicazione: (2023)

The Detection-Extraction Gap: Models Know the Answer Before They Can Say It
di: Wang, Hanyang, et al.
Pubblicazione: (2026)

Model Internals-based Answer Attribution for Trustworthy Retrieval-Augmented Generation
di: Qi, Jirui, et al.
Pubblicazione: (2024)

Train Once, Answer All: Many Pretraining Experiments for the Cost of One
di: Bordt, Sebastian, et al.
Pubblicazione: (2025)

Crystal-KV: Efficient KV Cache Management for Chain-of-Thought LLMs via Answer-First Principle
di: Wang, Zihan, et al.
Pubblicazione: (2026)

DiffuSpeech: Silent Thought, Spoken Answer via Unified Speech-Text Diffusion
di: Lou, Yuxuan, et al.
Pubblicazione: (2026)

Clinical QA 2.0: Multi-Task Learning for Answer Extraction and Categorization
di: Pattnayak, Priyaranjan, et al.
Pubblicazione: (2025)

ProfBench: Multi-Domain Rubrics requiring Professional Knowledge to Answer and Judge
di: Wang, Zhilin, et al.
Pubblicazione: (2025)

Seeing Isn't Knowing: Do VLMs Know When Not to Answer Spatial Questions (and Why)?
di: Zhang, Yue, et al.
Pubblicazione: (2026)

Grounded Cache Routing for Retrieval-Augmented Generation: When Is It Safe to Reuse an Answer?
di: Shah, Syed Huma
Pubblicazione: (2026)