paper-with-me

홈 › Papers

Halu-J: Critique-Based Hallucination Judge

2024-07-17 · Binjie Wang, Steffi Chern, Ethan Chern, PengFei Liu

Large language models (LLMs) frequently generate non-factual content, known as hallucinations. Existing retrieval-augmented-based hallucination detection approaches typically address this by framing it as a classification task, evaluating hallucinations based on their consistency with retrieved evidence. However, this approach usually lacks detailed explanations for these evaluations and does not assess the reliability of these explanations. Furthermore, deficiencies in retrieval systems can lead to irrelevant or partially relevant evidence retrieval, impairing the detection process. Moreover, while real-world hallucination detection requires analyzing multiple pieces of evidence, current systems usually treat all evidence uniformly without considering its relevance to the content. To address these challenges, we introduce Halu-J, a critique-based hallucination judge with 7 billion parameters. Halu-J enhances hallucination detection by selecting pertinent evidence and providing detailed critiques. Our experiments indicate that Halu-J outperforms GPT-4o in multiple-evidence hallucination detection and matches its capability in critique generation and evidence selection. We also introduce ME-FEVER, a new dataset designed for multiple-evidence hallucination detection. Our code and dataset can be found in https://github.com/GAIR-NLP/factool .

📄 PDF Abstract BibTeX arXiv:2407.12943

Code (1)

gair-nlp/factool 공식 구현

Tasks

Evidence SelectionHallucinationRetrieval

Similar Papers 제목 키워드 기반

HaluNet: Learning Hallucination Risk from Internal Signals in LLM Question Answering

2025-12-31 · Chaodong Tong, Qi Zhang, Zhuojun Jiang, Lei Jiang 외 arxiv

Large language models (LLMs) achieve strong question answering (QA) performance but can produce fluent answers unsupported by available evidence. Existing hallucination detectors often rely on external verification, repe…

Question AnsweringNatural Questions

Lynx: An Open Source Hallucination Evaluation Model

2024-07-11 · Selvan Sunitha Ravi, Bartosz Mielczarek, Anand Kannappan, Douwe Kiela 외

Retrieval Augmented Generation (RAG) techniques aim to mitigate hallucinations in Large Language Models (LLMs). However, LLMs can still produce information that is unsupported or contradictory to the retrieved contexts. …

HallucinationHallucination EvaluationmodelRAG+2

Factored Verification: Detecting and Reducing Hallucination in Summaries of Academic Papers

2023-10-16 · Charlie George, Andreas Stuhlmüller

Hallucination plagues even frontier LLMs--but how bad is it really for summarizing academic papers? We evaluate Factored Verification, a simple automated method for detecting hallucinations in abstractive summaries. This…

16kHallucination

Small Agent Can Also Rock! Empowering Small Language Models as Hallucination Detector

2024-06-17 · Xiaoxue Cheng, Junyi Li, Wayne Xin Zhao, Hongzhi Zhang 외

Hallucination detection is a challenging task for large language models (LLMs), and existing studies heavily rely on powerful closed-source LLMs such as GPT-4. In this paper, we propose an autonomous LLM-based agent fram…

2kHallucination

HaluMem: Evaluating Hallucinations in Memory Systems of Agents

2025-11-05 · Ding Chen, Simin Niu, Kehang Li, Peng Liu 외 arxiv

Memory systems are key components that enable AI systems such as LLMs and AI agents to achieve long-term learning and sustained interaction. However, during memory storage and retrieval, these systems frequently exhibit …

Question Answering