Bridging External and Parametric Knowledge: Mitigating Hallucination of LLMs with Shared-Private Semantic Synergy in Dual-Stream Knowledge

• URL: http://arxiv.org/abs/2506.06240v1
• Date: Fri, 06 Jun 2025 17:00:23 GMT
• Title: Bridging External and Parametric Knowledge: Mitigating Hallucination of LLMs with Shared-Private Semantic Synergy in Dual-Stream Knowledge
• Authors: Yi Sui, Chaozhuo Li, Chen Zhang, Dawei song, Qiuchi Li,
• Abstract summary: We propose a Dual-Stream Knowledge-Augmented Framework for Shared-Private Semantic Synergy (DSSP-RAG)<n>Central to the framework is a novel approach that refines self-attention into a mixed-attention, distinguishing shared and private semantics for a controlled internal-external knowledge integration.<n>Experiments on benchmark datasets show that DSSP-RAG can effectively resolve conflicts and enhance the complementarity of dual-stream knowledge, leading to superior performance over strong baselines.
• Score: 19.767087192966223
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Retrieval-augmented generation (RAG) is a cost-effective approach to mitigate the hallucination of Large Language Models (LLMs) by incorporating the retrieved external knowledge into the generation process. However, external knowledge may conflict with the parametric knowledge of LLMs. Furthermore, current LLMs lack inherent mechanisms for resolving such knowledge conflicts, making traditional RAG methods suffer from degraded performance and stability. Thus, we propose a Dual-Stream Knowledge-Augmented Framework for Shared-Private Semantic Synergy (DSSP-RAG). Central to the framework is a novel approach that refines self-attention into a mixed-attention, distinguishing shared and private semantics for a controlled internal-external knowledge integration. To effectively facilitate DSSP in RAG, we further introduce an unsupervised hallucination detection method based on cognitive uncertainty, ensuring the necessity of introducing knowledge, and an Energy Quotient (EQ) based on attention difference matrices to reduce noise in the retrieved external knowledge. Extensive experiments on benchmark datasets show that DSSP-RAG can effectively resolve conflicts and enhance the complementarity of dual-stream knowledge, leading to superior performance over strong baselines.

Related papers

• Unveiling Knowledge Utilization Mechanisms in LLM-based Retrieval-Augmented Generation [77.10390725623125]
  retrieval-augmented generation (RAG) is widely employed to expand their knowledge scope.<n>Since RAG has shown promise in knowledge-intensive tasks like open-domain question answering, its broader application to complex tasks and intelligent assistants has further advanced its utility.<n>We present a systematic investigation of the intrinsic mechanisms by which RAGs integrate internal (parametric) and external (retrieved) knowledge.
  arXiv  Detail & Related papers  (2025-05-17T13:13:13Z)
• Reinforced Internal-External Knowledge Synergistic Reasoning for Efficient Adaptive Search Agent [13.38972389476201]
  This paper introduces the Reinforced Internal-External Knowledge Synergistic Reasoning Agent (IKEA)<n>IKEA could indentify its own knowledge boundary and prioritize the utilization of internal knowledge, resorting to external search only when internal knowledge is deemed insufficient.<n>IKEA significantly outperforms baseline methods, reduces retrieval frequency significantly, and exhibits robust generalization capabilities.
  arXiv  Detail & Related papers  (2025-05-12T14:21:57Z)
• R1-Searcher: Incentivizing the Search Capability in LLMs via Reinforcement Learning [87.30285670315334]
  textbfR1-Searcher is a novel two-stage outcome-based RL approach designed to enhance the search capabilities of Large Language Models.<n>Our framework relies exclusively on RL, without requiring process rewards or distillation for a cold start.<n>Our experiments demonstrate that our method significantly outperforms previous strong RAG methods, even when compared to the closed-source GPT-4o-mini.
  arXiv  Detail & Related papers  (2025-03-07T17:14:44Z)
• ParamMute: Suppressing Knowledge-Critical FFNs for Faithful Retrieval-Augmented Generation [91.20492150248106]
  Large language models (LLMs) integrated with retrieval-augmented generation (RAG) have improved factuality by grounding outputs in external evidence.<n>We investigate the internal mechanisms behind unfaithful generation and identify a subset of mid-to-deep feed-forward networks (FFNs) that are disproportionately activated in such cases.<n>We propose Parametric Knowledge Muting through FFN Suppression (ParamMute), a framework that improves contextual faithfulness by suppressing the activation of unfaithfulness-associated FFNs and calibrating the model toward retrieved knowledge.
  arXiv  Detail & Related papers  (2025-02-21T15:50:41Z)
• UniKnow: A Unified Framework for Reliable Language Model Behavior across Parametric and External Knowledge [14.81530569173485]
  We introduce UniKnow, a Unified framework for reliable LM behavior across parametric and external knowledge.<n>UniKnow enables controlled evaluation across knowledge scenarios such as knowledge conflict, distraction, and absence conditions.
  arXiv  Detail & Related papers  (2025-02-19T11:49:23Z)
• GIVE: Structured Reasoning of Large Language Models with Knowledge Graph Inspired Veracity Extrapolation [108.2008975785364]
  Graph Inspired Veracity Extrapolation (GIVE) is a novel reasoning method that merges parametric and non-parametric memories to improve accurate reasoning with minimal external input.<n>GIVE guides the LLM agent to select the most pertinent expert data (observe), engage in query-specific divergent thinking (reflect), and then synthesize this information to produce the final output (speak)
  arXiv  Detail & Related papers  (2024-10-11T03:05:06Z)
• Astute RAG: Overcoming Imperfect Retrieval Augmentation and Knowledge Conflicts for Large Language Models [20.605487145370752]
  We find that imperfect retrieval augmentation is inevitable, common, and harmful.<n>We propose Astute RAG, a novel RAG approach designed to be resilient to imperfect retrieval augmentation.<n>Experiments with Gemini and Claude demonstrate the superior performance of Astute RAG compared to previous robustness-enhanced RAG approaches.
  arXiv  Detail & Related papers  (2024-10-09T17:59:58Z)
• Evaluating the External and Parametric Knowledge Fusion of Large Language Models [72.40026897037814]
  We develop a systematic pipeline for data construction and knowledge infusion to simulate knowledge fusion scenarios. Our investigation reveals that enhancing parametric knowledge within LLMs can significantly bolster their capability for knowledge integration. Our findings aim to steer future explorations on harmonizing external and parametric knowledge within LLMs.
  arXiv  Detail & Related papers  (2024-05-29T11:48:27Z)
• 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)
• Knowledge Verification to Nip Hallucination in the Bud [69.79051730580014]
  We demonstrate the feasibility of mitigating hallucinations by verifying and minimizing the inconsistency between external knowledge present in the alignment data and the intrinsic knowledge embedded within foundation LLMs. We propose a novel approach called Knowledge Consistent Alignment (KCA), which employs a well-aligned LLM to automatically formulate assessments based on external knowledge. We demonstrate the superior efficacy of KCA in reducing hallucinations across six benchmarks, utilizing foundation LLMs of varying backbones and scales.
  arXiv  Detail & Related papers  (2024-01-19T15:39:49Z)

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.