Parameters vs. Context: Fine-Grained Control of Knowledge Reliance in Language Models

• URL: http://arxiv.org/abs/2503.15888v1
• Date: Thu, 20 Mar 2025 06:26:28 GMT
• Title: Parameters vs. Context: Fine-Grained Control of Knowledge Reliance in Language Models
• Authors: Baolong Bi, Shenghua Liu, Yiwei Wang, Yilong Xu, Junfeng Fang, Lingrui Mei, Xueqi Cheng,
• Abstract summary: Retrieval-Augmented Generation (RAG) mitigates hallucinations in Large Language Models (LLMs) by integrating external knowledge.<n>Conflicts between parametric knowledge and retrieved context pose challenges for RAGs.<n>We propose **CK-PLUG**, a plug-and-play method for controlling RAG's reliance on parametric and contextual knowledge.
• Score: 39.73834207174728
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Retrieval-Augmented Generation (RAG) mitigates hallucinations in Large Language Models (LLMs) by integrating external knowledge. However, conflicts between parametric knowledge and retrieved context pose challenges, particularly when retrieved information is unreliable or the model's internal knowledge is outdated. In such cases, LLMs struggle to determine whether to rely more on their own parameters or the conflicted context. To address this, we propose **CK-PLUG**, a plug-and-play method for controlling LLMs' reliance on parametric and contextual knowledge. We introduce a novel knowledge consistency metric, Confidence Gain, which detects knowledge conflicts by measuring entropy shifts in token probability distributions after context insertion. CK-PLUG then enables fine-grained control over knowledge preference by adjusting the probability distribution of tokens with negative confidence gain through a single tuning parameter. Experiments demonstrate CK-PLUG's ability to significantly regulate knowledge reliance in counterfactual RAG scenarios while maintaining generation fluency and knowledge accuracy. For instance, on Llama3-8B, memory recall (MR) of RAG response can be adjusted within a broad range (9.9%-71.9%), compared to the baseline of 42.1%. Moreover, CK-PLUG supports adaptive control based on the model's confidence in both internal and external knowledge, achieving consistent performance improvements across various general RAG tasks. Our code is available at: $\href{https://github.com/byronBBL/CK-PLUG}{\text{this https URL}}$.

Related papers

• Accommodate Knowledge Conflicts in Retrieval-augmented LLMs: Towards Reliable Response Generation in the Wild [11.058848731627233]
  Large language models (LLMs) have advanced information retrieval systems. LLMs often face knowledge conflicts between internal memory and retrievaled external information. We propose Swin-VIB, a novel framework that integrates a pipeline of variational information bottleneck models into adaptive augmentation of retrieved information.
  arXiv  Detail & Related papers  (2025-04-17T14:40:31Z)
• PIP-KAG: Mitigating Knowledge Conflicts in Knowledge-Augmented Generation via Parametric Pruning [92.07119924043461]
  Knowledge-Augmented Generation (KAG) has shown great promise in updating the internal memory of Large Language Models (LLMs)<n>Current approaches to mitigating these conflicts mainly focus on improving external knowledge utilization.<n>We propose a ParametrIc Pruning-based Knowledge-Augmented Generation (PIP-KAG) approach, which prunes internal knowledge of LLMs.
  arXiv  Detail & Related papers  (2025-02-21T15:50:41Z)
• TrustRAG: Enhancing Robustness and Trustworthiness in RAG [31.231916859341865]
  TrustRAG is a framework that systematically filters compromised and irrelevant contents before they are retrieved for generation.<n>TrustRAG delivers substantial improvements in retrieval accuracy, efficiency, and attack resistance compared to existing approaches.
  arXiv  Detail & Related papers  (2025-01-01T15:57:34Z)
• To Trust or Not to Trust? Enhancing Large Language Models' Situated Faithfulness to External Contexts [10.748768620243982]
  Large Language Models (LLMs) are often augmented with external contexts, such as those used in retrieval-augmented generation (RAG)<n>We show that when provided with both correct and incorrect contexts, both open-source and proprietary models tend to overly rely on external information.<n>We propose two approaches: Self-Guided Confidence Reasoning (SCR) and Rule-Based Confidence Reasoning (RCR)
  arXiv  Detail & Related papers  (2024-10-18T17:59:47Z)
• Astute RAG: Overcoming Imperfect Retrieval Augmentation and Knowledge Conflicts for Large Language Models [20.605487145370752]
  We find that imperfect retrieval augmentation might be inevitable and quite harmful, through controlled analysis under realistic conditions. We propose Astute RAG, a novel RAG approach that adaptively elicits essential information from LLMs' internal knowledge. Further analysis reveals that Astute RAG effectively resolves knowledge conflicts, improving the reliability and trustworthiness of RAG systems.
  arXiv  Detail & Related papers  (2024-10-09T17:59:58Z)
• Retrieving, Rethinking and Revising: The Chain-of-Verification Can Improve Retrieval Augmented Generation [38.80878966092216]
  Recent Retrieval Augmented Generation (RAG) aims to enhance Large Language Models (LLMs) We propose the chain-of-verification (CoV-RAG) to enhance the external retrieval correctness and internal generation consistency.
  arXiv  Detail & Related papers  (2024-10-08T08:34:54Z)
• SFR-RAG: Towards Contextually Faithful LLMs [57.666165819196486]
  Retrieval Augmented Generation (RAG) is a paradigm that integrates external contextual information with large language models (LLMs) to enhance factual accuracy and relevance. We introduce SFR-RAG, a small LLM that is instruction-textual with an emphasis on context-grounded generation and hallucination. We also present ConBench, a new evaluation framework compiling multiple popular and diverse RAG benchmarks.
  arXiv  Detail & Related papers  (2024-09-16T01:08:18Z)
• 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)
• ActiveRAG: Autonomously Knowledge Assimilation and Accommodation through Retrieval-Augmented Agents [49.30553350788524]
  Retrieval-Augmented Generation (RAG) enables Large Language Models (LLMs) to leverage external knowledge. Existing RAG models often treat LLMs as passive recipients of information. We introduce ActiveRAG, a multi-agent framework that mimics human learning behavior.
  arXiv  Detail & Related papers  (2024-02-21T06:04:53Z)
• R-Tuning: Instructing Large Language Models to Say `I Don't Know' [66.11375475253007]
  Large language models (LLMs) have revolutionized numerous domains with their impressive performance but still face their challenges. Previous instruction tuning methods force the model to complete a sentence no matter whether the model knows the knowledge or not. We present a new approach called Refusal-Aware Instruction Tuning (R-Tuning) Experimental results demonstrate R-Tuning effectively improves a model's ability to answer known questions and refrain from answering unknown questions.
  arXiv  Detail & Related papers  (2023-11-16T08:45:44Z)
• Seeking Neural Nuggets: Knowledge Transfer in Large Language Models from a Parametric Perspective [106.92016199403042]
  We empirically investigate knowledge transfer from larger to smaller models through a parametric perspective. We employ sensitivity-based techniques to extract and align knowledge-specific parameters between different large language models. Our findings highlight the critical factors contributing to the process of parametric knowledge transfer.
  arXiv  Detail & Related papers  (2023-10-17T17:58:34Z)

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.