paper-with-me

Papers

LLM Factoscope: Uncovering LLMs' Factual Discernment through Inner States Analysis

2023-12-27 · Jinwen He, Yujia Gong, Kai Chen, Zijin Lin, Chengan Wei, Yue Zhao

Large Language Models (LLMs) have revolutionized various domains with extensive knowledge and creative capabilities. However, a critical issue with LLMs is their tendency to produce outputs that diverge from factual reality. This phenomenon is particularly concerning in sensitive applications such as medical consultation and legal advice, where accuracy is paramount. In this paper, we introduce the LLM factoscope, a novel Siamese network-based model that leverages the inner states of LLMs for factual detection. Our investigation reveals distinguishable patterns in LLMs' inner states when generating factual versus non-factual content. We demonstrate the LLM factoscope's effectiveness across various architectures, achieving over 96% accuracy in factual detection. Our work opens a new avenue for utilizing LLMs' inner states for factual detection and encourages further exploration into LLMs' inner workings for enhanced reliability and transparency.

📄 PDF Abstract BibTeX arXiv:2312.16374

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

DHP Benchmark: Are LLMs Good NLG Evaluators?

2024-08-25 · Yicheng Wang, Jiayi Yuan, Yu-Neng Chuang, Zhuoer Wang 외

Large Language Models (LLMs) are increasingly serving as evaluators in Natural Language Generation (NLG) tasks. However, the capabilities of LLMs in scoring NLG quality remain inadequately explored. Current studies depen…

Benchmarkingnlg evaluationQuestion AnsweringStory Completion+1

TiEBe: Tracking Language Model Recall of Notable Worldwide Events Through Time

2025-01-13 · Thales Sales Almeida, Giovana Kerche Bonás, João Guilherme Alves Santos, Hugo Abonizio 외

As the knowledge landscape evolves and large language models (LLMs) become increasingly widespread, there is a growing need to keep these models updated with current events. While existing benchmarks assess general factu…

Continual LearningLanguage ModelingLanguage Modelling

How Do Multilingual Models Remember? Investigating Multilingual Factual Recall Mechanisms

2024-10-18 · Constanza Fierro, Negar Foroutan, Desmond Elliott, Anders Søgaard

Large Language Models (LLMs) store and retrieve vast amounts of factual knowledge acquired during pre-training. Prior research has localized and identified mechanisms behind knowledge recall; however, it has primarily fo…

The Earth is Flat? Unveiling Factual Errors in Large Language Models

2024-01-01 · Wenxuan Wang, Juluan Shi, Zhaopeng Tu, Youliang Yuan 외

Large Language Models (LLMs) like ChatGPT are foundational in various applications due to their extensive knowledge from pre-training and fine-tuning. Despite this, they are prone to generating factual and commonsense er…

In-Context LearningMultiple-choice

Beyond Jailbreaks: Revealing Stealthier and Broader LLM Security Risks Stemming from Alignment Failures

2025-06-09 · Yukai Zhou, Sibei Yang, Wenjie Wang

Large language models (LLMs) are increasingly deployed in real-world applications, raising concerns about their security. While jailbreak attacks highlight failures under overtly harmful queries, they overlook a critical…