paper-with-me

Papers

Improving Model Factuality with Fine-grained Critique-based Evaluator

2024-10-24 · Yiqing Xie, Wenxuan Zhou, Pradyot Prakash, Di Jin, Yuning Mao, Quintin Fettes, Arya Talebzadeh, Sinong Wang, Han Fang, Carolyn Rose, Daniel Fried, Hejia Zhang

Factuality evaluation aims to detect factual errors produced by language models (LMs) and hence guide the development of more factual models. Towards this goal, we train a factuality evaluator, FenCE, that provides LM generators with claim-level factuality feedback. We conduct data augmentation on a combination of public judgment datasets to train FenCE to (1) generate textual critiques along with scores and (2) make claim-level judgment based on diverse source documents obtained by various tools. We then present a framework that leverages FenCE to improve the factuality of LM generators by constructing training data. Specifically, we generate a set of candidate responses, leverage FenCE to revise and score each response without introducing lesser-known facts, and train the generator by preferring highly scored revised responses. Experiments show that our data augmentation methods improve the evaluator's accuracy by 2.9% on LLM-AggreFact. With FenCE, we improve Llama2-7B-chat and Llama3-8B-chat's factuality rate by 16.86% and 14.45% on FActScore, outperforming state-of-the-art factuality finetuning methods by 8.83% and 6.96%.

📄 PDF Abstract BibTeX arXiv:2410.18359

Code (0)

등록된 구현이 없습니다.

Tasks

Data Augmentation

Methods 이 논문이 사용한 방법론

SET Dynamic Sparse Training method where weight mask is updated randomly periodically

Similar Papers 제목 키워드 기반

FELM: Benchmarking Factuality Evaluation of Large Language Models

2023-10-01 · NeurIPS 2023 11 · Shiqi Chen, Yiran Zhao, Jinghan Zhang, I-Chun Chern 외

Assessing factuality of text generated by large language models (LLMs) is an emerging yet crucial research area, aimed at alerting users to potential errors and guiding the development of more reliable LLMs. Nonetheless,…

BenchmarkingMathRetrievalWorld Knowledge

Learning to Refine with Fine-Grained Natural Language Feedback

2024-07-02 · Manya Wadhwa, Xinyu Zhao, Junyi Jessy Li, Greg Durrett

Recent work has explored the capability of large language models (LLMs) to identify and correct errors in LLM-generated responses. These refinement approaches frequently evaluate what sizes of models are able to do refin…

The Critique of Critique

2024-01-09 · Shichao Sun, Junlong Li, Weizhe Yuan, Ruifeng Yuan 외

Critique, as a natural language description for assessing the quality of model-generated content, has played a vital role in the training, evaluation, and refinement of LLMs. However, a systematic method to evaluate the …

Question Answering

FactLens: Benchmarking Fine-Grained Fact Verification

2024-11-08 · Kushan Mitra, Dan Zhang, Sajjadur Rahman, Estevam Hruschka

Large Language Models (LLMs) have shown impressive capability in language generation and understanding, but their tendency to hallucinate and produce factually incorrect information remains a key limitation. To verify LL…

BenchmarkingFact VerificationText Generation

RationalRewards: Reasoning Rewards Scale Visual Generation Both Training and Test Time

2026-04-13 · Haozhe Wang, Cong Wei, Weiming Ren, Jiaming Liu 외 arxiv

Most reward models for visual generation reduce rich human judgments to a single unexplained score, discarding the reasoning that underlies preference. We show that teaching reward models to produce explicit, multi-dimen…

Reinforcement Learning