paper-with-me

홈 › Papers

LM vs LM: Detecting Factual Errors via Cross Examination

2023-05-22 · Roi Cohen, May Hamri, Mor Geva, Amir Globerson

A prominent weakness of modern language models (LMs) is their tendency to generate factually incorrect text, which hinders their usability. A natural question is whether such factual errors can be detected automatically. Inspired by truth-seeking mechanisms in law, we propose a factuality evaluation framework for LMs that is based on cross-examination. Our key idea is that an incorrect claim is likely to result in inconsistency with other claims that the model generates. To discover such inconsistencies, we facilitate a multi-turn interaction between the LM that generated the claim and another LM (acting as an examiner) which introduces questions to discover inconsistencies. We empirically evaluate our method on factual claims made by multiple recent LMs on four benchmarks, finding that it outperforms existing methods and baselines, often by a large gap. Our results demonstrate the potential of using interacting LMs for capturing factual errors.

📄 PDF Abstract BibTeX arXiv:2305.13281

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Detecting Errors through Ensembling Prompts (DEEP): An End-to-End LLM Framework for Detecting Factual Errors

2024-06-18 · Alex Chandler, Devesh Surve, Hui Su

Accurate text summarization is one of the most common and important tasks performed by Large Language Models, where the costs of human review for an entire document may be high, but the costs of errors in summarization m…

HallucinationLanguage ModelingLanguage ModellingLarge Language Model+1

Cross-Examination Framework: A Task-Agnostic Diagnostic for Information Fidelity in Text-to-Text Generation

2026-01-27 · Tathagata Raha, Clement Christophe, Nada Saadi, Hamza A Javed 외 arxiv

Traditional metrics like BLEU and BERTScore fail to capture semantic fidelity in generative text-to-text tasks. We adapt the Cross-Examination Framework (CEF) for a reference-free, multi-dimensional evaluation by treatin…

Text Generation

FLEEK: Factual Error Detection and Correction with Evidence Retrieved from External Knowledge

2023-10-26 · Farima Fatahi Bayat, Kun Qian, Benjamin Han, Yisi Sang 외

Detecting factual errors in textual information, whether generated by large language models (LLM) or curated by humans, is crucial for making informed decisions. LLMs' inability to attribute their claims to external know…

Attribute

Annotating and Detecting Fine-grained Factual Errors for Dialogue Summarization

2023-05-26 · Rongxin Zhu, Jianzhong Qi, Jey Han Lau

A series of datasets and models have been proposed for summaries generated for well-formatted documents such as news articles. Dialogue summaries, however, have been under explored. In this paper, we present the first da…

ArticlesDecoderMulti-Label ClassificationMUlTI-LABEL-ClASSIFICATION+1

SummExecEdit: A Factual Consistency Benchmark in Summarization with Executable Edits

2024-12-17 · Onkar Thorat, Philippe Laban, Chien-Sheng Wu

Detecting factual inconsistencies in summarization is critical, yet existing benchmarks lack the necessary challenge and interpretability for robust evaluation. In this paper, we introduce SummExecEdit, a novel benchmark…