Reducing Hallucinations in Summarization via Reinforcement Learning with Entity Hallucination Index
- URL: http://arxiv.org/abs/2507.22744v1
- Date: Wed, 30 Jul 2025 15:00:00 GMT
- Title: Reducing Hallucinations in Summarization via Reinforcement Learning with Entity Hallucination Index
- Authors: Praveenkumar Katwe, Rakesh Chandra, Balabantaray Kali, Prasad Vittala,
- Abstract summary: We introduce a rewarddriven fine-tuning framework to optimize for Entity Hallucination Index (EHI)<n>EHI is a metric designed to quantify the presence, correctness, and grounding of named entities in generated summaries.<n>Our approach does not rely on human-written factuality annotations, enabling scalable fine-tuning.
- Score: 2.2427832125073737
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: 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.
Related papers
- Mitigating Object Hallucinations via Sentence-Level Early Intervention [10.642552315531404]
Multimodal large language models (MLLMs) have revolutionized cross-modal understanding but continue to struggle with hallucinations.<n>We propose SENTINEL, a framework that eliminates dependency on human annotations.<n>Sentence-level Early iNtervention Through IN-domain prEference Learning can reduce hallucinations by over 90% compared to the original model.
arXiv Detail & Related papers (2025-07-16T17:55:43Z) - HalluLens: LLM Hallucination Benchmark [49.170128733508335]
Large language models (LLMs) often generate responses that deviate from user input or training data, a phenomenon known as "hallucination"<n>This paper introduces a comprehensive hallucination benchmark, incorporating both new extrinsic and existing intrinsic evaluation tasks.
arXiv Detail & Related papers (2025-04-24T13:40:27Z) - ANAH-v2: Scaling Analytical Hallucination Annotation of Large Language Models [65.12177400764506]
Large language models (LLMs) exhibit hallucinations in long-form question-answering tasks across various domains and wide applications.<n>Current hallucination detection and mitigation datasets are limited in domains and sizes.<n>This paper introduces an iterative self-training framework that simultaneously and progressively scales up the hallucination annotation dataset.
arXiv Detail & Related papers (2024-07-05T17:56:38Z) - Detecting and Mitigating Hallucination in Large Vision Language Models via Fine-Grained AI Feedback [40.930238150365795]
We propose detecting and mitigating hallucinations in Large Vision Language Models (LVLMs) via fine-grained AI feedback.<n>We generate a small-size hallucination annotation dataset by proprietary models.<n>Then, we propose a detect-then-rewrite pipeline to automatically construct preference dataset for training hallucination mitigating model.
arXiv Detail & Related papers (2024-04-22T14:46:10Z) - Retrieve Only When It Needs: Adaptive Retrieval Augmentation for Hallucination Mitigation in Large Language Models [68.91592125175787]
Hallucinations pose a significant challenge for the practical implementation of large language models (LLMs)
We present Rowen, a novel approach that enhances LLMs with a selective retrieval augmentation process tailored to address hallucinations.
arXiv Detail & Related papers (2024-02-16T11:55:40Z) - Alleviating Hallucinations of Large Language Models through Induced
Hallucinations [67.35512483340837]
Large language models (LLMs) have been observed to generate responses that include inaccurate or fabricated information.
We propose a simple textitInduce-then-Contrast Decoding (ICD) strategy to alleviate hallucinations.
arXiv Detail & Related papers (2023-12-25T12:32:49Z) - AutoHall: Automated Hallucination Dataset Generation for Large Language Models [56.92068213969036]
This paper introduces a method for automatically constructing model-specific hallucination datasets based on existing fact-checking datasets called AutoHall.
We also propose a zero-resource and black-box hallucination detection method based on self-contradiction.
arXiv Detail & Related papers (2023-09-30T05:20:02Z) - Hallucination Reduction in Long Input Text Summarization [2.6745438139282283]
Hallucination in text summarization poses significant obstacles to the accuracy and reliability of the generated summaries.
We have incorporated the techniques of data filtering and joint entity and summary generation (JAENS) in the fine-tuning of the Longformer-Decoder (LED) model.
Our experiments show that the fine-tuned LED model performs well in generating the paper abstract.
arXiv Detail & Related papers (2023-09-28T18:22:16Z) - Detecting Hallucinated Content in Conditional Neural Sequence Generation [165.68948078624499]
We propose a task to predict whether each token in the output sequence is hallucinated (not contained in the input)
We also introduce a method for learning to detect hallucinations using pretrained language models fine tuned on synthetic data.
arXiv Detail & Related papers (2020-11-05T00:18:53Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.