IRCAN: Mitigating Knowledge Conflicts in LLM Generation via Identifying and Reweighting Context-Aware Neurons

• URL: http://arxiv.org/abs/2406.18406v2
• Date: Thu, 14 Nov 2024 10:55:14 GMT
• Title: IRCAN: Mitigating Knowledge Conflicts in LLM Generation via Identifying and Reweighting Context-Aware Neurons
• Authors: Dan Shi, Renren Jin, Tianhao Shen, Weilong Dong, Xinwei Wu, Deyi Xiong,
• Abstract summary: Large language models (LLMs) encode a vast reservoir of knowledge after being trained on mass data. Recent studies disclose knowledge conflicts in LLM generation, wherein outdated or incorrect parametric knowledge contradicts new knowledge provided in the context. We propose a novel framework, IRCAN, to capitalize on neurons that are crucial in processing contextual cues.
• Score: 35.932259793728
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: It is widely acknowledged that large language models (LLMs) encode a vast reservoir of knowledge after being trained on mass data. Recent studies disclose knowledge conflicts in LLM generation, wherein outdated or incorrect parametric knowledge (i.e., encoded knowledge) contradicts new knowledge provided in the context. To mitigate such knowledge conflicts, we propose a novel framework, IRCAN (Identifying and Reweighting Context-Aware Neurons) to capitalize on neurons that are crucial in processing contextual cues. Specifically, IRCAN first identifies neurons that significantly contribute to context processing, utilizing a context-aware attribution score derived from integrated gradients. Subsequently, the identified context-aware neurons are strengthened via reweighting. In doing so, we steer LLMs to generate context-sensitive outputs with respect to the new knowledge provided in the context. Extensive experiments conducted across a variety of models and tasks demonstrate that IRCAN not only achieves remarkable improvements in handling knowledge conflicts but also offers a scalable, plug-and-play solution that can be integrated seamlessly with existing models. Our codes are released at https://github.com/danshi777/IRCAN.

Related papers

• Systematic Knowledge Injection into Large Language Models via Diverse Augmentation for Domain-Specific RAG [24.660769275714685]
  Retrieval-Augmented Generation (RAG) has emerged as a prominent method for incorporating domain knowledge into Large Language Models (LLMs) We present a novel framework that significantly enhances the fine-tuning process by augmenting the training data in two ways -- context augmentation and knowledge paraphrasing.
  arXiv  Detail & Related papers  (2025-02-12T12:39:51Z)
• Enhancing Contextual Understanding in Large Language Models through Contrastive Decoding [9.2433070542025]
  Large language models (LLMs) tend to inadequately integrate input context during text generation. We introduce a novel approach integrating contrastive decoding with adversarial irrelevant passages as negative samples.
  arXiv  Detail & Related papers  (2024-05-04T20:38:41Z)
• LLMs' Reading Comprehension Is Affected by Parametric Knowledge and Struggles with Hypothetical Statements [59.71218039095155]
  Task of reading comprehension (RC) provides a primary means to assess language models' natural language understanding (NLU) capabilities. If the context aligns with the models' internal knowledge, it is hard to discern whether the models' answers stem from context comprehension or from internal information. To address this issue, we suggest to use RC on imaginary data, based on fictitious facts and entities.
  arXiv  Detail & Related papers  (2024-04-09T13:08:56Z)
• Untangle the KNOT: Interweaving Conflicting Knowledge and Reasoning Skills in Large Language Models [51.72963030032491]
  Knowledge documents for large language models (LLMs) may conflict with the memory of LLMs due to outdated or incorrect knowledge. We construct a new dataset, dubbed KNOT, for knowledge conflict resolution examination in the form of question answering.
  arXiv  Detail & Related papers  (2024-04-04T16:40:11Z)
• Robust and Scalable Model Editing for Large Language Models [75.95623066605259]
  We propose EREN (Edit models by REading Notes) to improve the scalability and robustness of LLM editing. Unlike existing techniques, it can integrate knowledge from multiple edits, and correctly respond to syntactically similar but semantically unrelated inputs.
  arXiv  Detail & Related papers  (2024-03-26T06:57:23Z)
• A Comprehensive Study of Knowledge Editing for Large Language Models [82.65729336401027]
  Large Language Models (LLMs) have shown extraordinary capabilities in understanding and generating text that closely mirrors human communication. This paper defines the knowledge editing problem and provides a comprehensive review of cutting-edge approaches. We introduce a new benchmark, KnowEdit, for a comprehensive empirical evaluation of representative knowledge editing approaches.
  arXiv  Detail & Related papers  (2024-01-02T16:54:58Z)
• UNTER: A Unified Knowledge Interface for Enhancing Pre-trained Language Models [100.4659557650775]
  We propose a UNified knowledge inTERface, UNTER, to provide a unified perspective to exploit both structured knowledge and unstructured knowledge. With both forms of knowledge injected, UNTER gains continuous improvements on a series of knowledge-driven NLP tasks.
  arXiv  Detail & Related papers  (2023-05-02T17:33:28Z)
• Knowledge Infused Decoding [46.09844215234235]
  Knowledge Infused Decoding (KID) is a novel decoding algorithm for generative language models (LMs) KID dynamically infuses external knowledge into each step of the LM decoding. Human evaluation confirms KID's ability to generate more relevant and factual language for the input context.
  arXiv  Detail & Related papers  (2022-04-06T20:58:32Z)

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.