paper-with-me

홈 › Papers

FactPEGASUS: Factuality-Aware Pre-training and Fine-tuning for Abstractive Summarization

2022-05-16 · NAACL 2022 7 · David Wan, Mohit Bansal

We present FactPEGASUS, an abstractive summarization model that addresses the problem of factuality during pre-training and fine-tuning: (1) We augment the sentence selection strategy of PEGASUS's (Zhang et al., 2020) pre-training objective to create pseudo-summaries that are both important and factual; (2) We introduce three complementary components for fine-tuning. The corrector removes hallucinations present in the reference summary, the contrastor uses contrastive learning to better differentiate nonfactual summaries from factual ones, and the connector bridges the gap between the pre-training and fine-tuning for better transfer of knowledge. Experiments on three downstream tasks demonstrate that FactPEGASUS substantially improves factuality evaluated by multiple automatic metrics and humans. Our thorough analysis suggests that FactPEGASUS is more factual than using the original pre-training objective in zero-shot and few-shot settings, retains factual behavior more robustly than strong baselines, and does not rely entirely on becoming more extractive to improve factuality. Our code and data are publicly available at: https://github.com/meetdavidwan/factpegasus

📄 PDF Abstract BibTeX arXiv:2205.07830

Code (1)

meetdavidwan/factpegasus 공식 구현 pytorch

Tasks

Abstractive Text SummarizationContrastive LearningSentence

Methods 이 논문이 사용한 방법론

Contrastive Learning 설명 없음

Similar Papers 제목 키워드 기반

FLAME: Factuality-Aware Alignment for Large Language Models

2024-05-02 · Sheng-Chieh Lin, Luyu Gao, Barlas Oguz, Wenhan Xiong 외

Alignment is a standard procedure to fine-tune pre-trained large language models (LLMs) to follow natural language instructions and serve as helpful AI assistants. We have observed, however, that the conventional alignme…

HallucinationInstruction FollowingReinforcement Learning (RL)

The Curious Case of Factuality Finetuning: Models' Internal Beliefs Can Improve Factuality

2025-07-11 · Benjamin Newman, Abhilasha Ravichander, Jaehun Jung, Rui Xin 외 arxiv

Language models are prone to hallucination - generating text that is factually incorrect. Finetuning models on high-quality factual information can potentially reduce hallucination, but concerns remain; obtaining factual…

The Hallucination Dilemma: Factuality-Aware Reinforcement Learning for Large Reasoning Models

2025-05-30 · Junyi Li, Hwee Tou Ng

Large language models (LLMs) have significantly advanced in reasoning tasks through reinforcement learning (RL) optimization, achieving impressive capabilities across various challenging benchmarks. However, our empirica…

HallucinationMathematical ReasoningReinforcement Learning (RL)

Understanding Finetuning for Factual Knowledge Extraction

2024-06-20 · Gaurav Ghosal, Tatsunori Hashimoto, aditi raghunathan

In this work, we study the impact of QA fine-tuning data on downstream factuality. We show that fine-tuning on lesser-known facts that are poorly stored during pretraining yields significantly worse factuality than fine-…

MMLUQuestion Answering

Beyond Under-Alignment: Atomic Preference Enhanced Factuality Tuning for Large Language Models

2024-06-18 · Hongbang Yuan, Yubo Chen, Pengfei Cao, Zhuoran Jin 외

Large language models (LLMs) have achieved remarkable success but still tend to generate factually erroneous responses, a phenomenon known as hallucination. A recent trend is to use preference learning to fine-tune model…

Hallucination