# Gradient-guided Attention Map Editing: Towards Efficient Contextual Hallucination Mitigation

arXiv: https://arxiv.org/abs/2503.08963 · HTML: https://mlsanity.com/paper/2503.08963/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 33 references that are in the map.
- First posted on arXiv 11 Mar 2025.

## Builds on (most cited first, 21 of 21)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Lost in the Middle: How Language Models Use Long Contexts](https://mlsanity.com/paper/2307.03172/) (2023)
- [TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension](https://mlsanity.com/paper/1705.03551/) (2017)
- [Retrieval-Augmented Generation for Large Language Models: A Survey](https://mlsanity.com/paper/2312.10997/) (2023)
- [Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone](https://mlsanity.com/paper/2404.14219/) (2024)
- [Understanding intermediate layers using linear classifier probes](https://mlsanity.com/paper/1610.01644/) (2016)
- [Don't Give Me the Details, Just the Summary! Topic-Aware Convolutional Neural Networks for Extreme Summarization](https://mlsanity.com/paper/1808.08745/) (2018)
- [Inference-Time Intervention: Eliciting Truthful Answers from a Language Model](https://mlsanity.com/paper/2306.03341/) (2023)
- [Are Sixteen Heads Really Better than One?](https://mlsanity.com/paper/1905.10650/) (2019)
- [Abstractive Text Summarization Using Sequence-to-Sequence RNNs and Beyond](https://mlsanity.com/paper/1602.06023/) (2016)
- [Plug and Play Language Models: A Simple Approach to Controlled Text Generation](https://mlsanity.com/paper/1912.02164/) (2019)
- [Fine-Tuning or Retrieval? Comparing Knowledge Injection in LLMs](https://mlsanity.com/paper/2312.05934/) (2023)
- [Lookback Lens: Detecting and Mitigating Contextual Hallucinations in Large Language Models Using Only Attention Maps](https://mlsanity.com/paper/2407.07071/) (2024)
- [TruthX: Alleviating Hallucinations by Editing Large Language Models in Truthful Space](https://mlsanity.com/paper/2402.17811/) (2024)
- [Unveiling and Harnessing Hidden Attention Sinks: Enhancing Large Language Models without Training through Attention Calibration](https://mlsanity.com/paper/2406.15765/) (2024)
- [Mutual Information Alleviates Hallucinations in Abstractive Summarization](https://mlsanity.com/paper/2210.13210/) (2022)
- [In-Context Sharpness as Alerts: An Inner Representation Perspective for Hallucination Mitigation](https://mlsanity.com/paper/2403.01548/) (2024)
- [Hallucination Detection and Hallucination Mitigation: An Investigation](https://mlsanity.com/paper/2401.08358/) (2024)
- [Constructing Benchmarks and Interventions for Combating Hallucinations in LLMs](https://mlsanity.com/paper/2404.09971/) (2024)
- [Extending Token Computation for LLM Reasoning](https://mlsanity.com/paper/2403.14932/) (2024)

## Built on by (most cited first, 3 of 3)

- [DocMEdit: Towards Document-Level Model Editing](https://mlsanity.com/paper/2505.19572/) (2025)
- [On the Nature of Attention Sink that Shapes Decoding Strategy in Omni-LLMs](https://mlsanity.com/paper/2603.14337/) (2026)
- [Automated Attention Pattern Discovery at Scale in Large Language Models](https://mlsanity.com/paper/2604.03764/) (2026)

## Abstract (arXiv)

In tasks like summarization and open-book question answering (QA), Large Language Models (LLMs) often encounter "contextual hallucination", where they produce irrelevant or incorrect responses despite having access to accurate source information. This typically occurs because these models tend to prioritize self-generated content over the input context, causing them to disregard pertinent details. To address this challenge, we introduce a novel method called "Guided Attention Map Editing" (GAME), which dynamically adjusts attention maps to improve contextual relevance. During inference, GAME employs a trained classifier to identify attention maps prone to inducing hallucinations and executes targeted interventions. These interventions, guided by gradient-informed "edit directions'', strategically redistribute attention weights across various heads to effectively reduce hallucination. Comprehensive evaluations on challenging summarization and open-book QA tasks show that GAME consistently reduces hallucinations across a variety of open-source models. Specifically, GAME reduces hallucinations by 10% in the XSum summarization task while achieving a 7X speed-up in computational efficiency compared to the state-of-the-art baselines.