paper-with-me

홈 › Papers

Reducing Hallucinations in Summarization via Reinforcement Learning with Entity Hallucination Index

2025-07-30 · Praveenkumar Katwe, Rakesh Chandra, Balabantaray Kali, Prasad Vittala arxiv

Reducing hallucinations in abstractive summarization remains a critical challenge for deploying language models (LMs) in real-world settings. In this work, we introduce a rewarddriven fine-tuning framework that explicitly optimizes for Entity Hallucination Index (EHI), a metric designed to quantify the presence, correctness, and grounding of named entities in generated summaries. Given a corpus of meeting transcripts, we first generate baseline summaries using a pre-trained LM and compute EHI scores via automatic entity extraction and matching. We then apply reinforcement learning to fine-tune the model parameters, using EHI as a reward signal to bias generation toward entity-faithful outputs. Our approach does not rely on human-written factuality annotations, enabling scalable fine-tuning. Experiments demonstrate consistent improvements in EHI across datasets, with qualitative analysis revealing a significant reduction in entity-level hallucinations without degradation in fluency or informativeness. We release a reproducible Colab pipeline, facilitating further research on hallucination-aware model fine-tuning using lightweight, hallucintion metrics like EHI.

📄 PDF Abstract BibTeX arXiv:2507.22744

Code (0)

등록된 구현이 없습니다.

Tasks

Reinforcement Learning

Similar Papers 제목 키워드 기반

Hallucination Diversity-Aware Active Learning for Text Summarization

2024-04-02 · Yu Xia, Xu Liu, Tong Yu, Sungchul Kim 외

Large Language Models (LLMs) have shown propensity to generate hallucinated outputs, i.e., texts that are factually incorrect or unsupported. Existing methods for alleviating hallucinations typically require costly human…

Active LearningDiversityHallucinationText Summarization

Hallucinated but Factual! Inspecting the Factuality of Hallucinations in Abstractive Summarization

2021-10-16 · ACL ARR October 2021 10 · Anonymous

State-of-the-art abstractive summarization systems often generate hallucinations; i.e., content that is not directly inferable from the source text. Despite being assumed to be incorrect, we find that much hallucinated c…

Abstractive Text SummarizationReinforcement Learning (RL)World Knowledge

Reducing Hallucinations in Entity Abstract Summarization with Facts-Template Decomposition

2024-02-29 · Fangwei Zhu, Peiyi Wang, Zhifang Sui

Entity abstract summarization aims to generate a coherent description of a given entity based on a set of relevant Internet documents. Pretrained language models (PLMs) have achieved significant success in this task, but…

Hallucinated but Factual! Inspecting the Factuality of Hallucinations in Abstractive Summarization

2021-08-30 · ACL 2022 5 · Meng Cao, Yue Dong, Jackie Chi Kit Cheung

State-of-the-art abstractive summarization systems often generate \emph{hallucinations}; i.e., content that is not directly inferable from the source text. Despite being assumed incorrect, we find that much hallucinated …

Abstractive Text SummarizationReinforcement Learning (RL)World Knowledge

Hallucination Reduction in Long Input Text Summarization

2023-09-28 · Tohida Rehman, Ronit Mandal, Abhishek Agarwal, Debarshi Kumar Sanyal

Hallucination in text summarization refers to the phenomenon where the model generates information that is not supported by the input source document. Hallucination poses significant obstacles to the accuracy and reliabi…

DecoderHallucinationText Summarization