Understanding the Interplay between LLMs' Utilisation of Parametric and Contextual Knowledge: A keynote at ECIR 2025

2026-03-10

AI Summary

This work proposes a diagnostic testing methodology to investigate how large language models often neglect or misapply relevant information in knowledge-intensive tasks due to conflicts between their parametric knowledge and externally retrieved context. By integrating a knowledge assessment framework with contextual effectiveness analysis, the study systematically uncovers the internal mechanisms underlying such knowledge conflicts and identifies key characteristics that enable successful integration of external knowledge. The findings reveal systematic biases in how models utilize stored versus retrieved knowledge, offering both theoretical insights and practical guidance for improving knowledge updating and context fusion strategies in language models.

Technology Category

• Knowledge Representation and Reasoning: Knowledge Acquisition
• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval
• Natural Language Processing: Interpretability, Analysis, and Evaluation of NLP Models

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking

Abstract

Language Models (LMs) acquire parametric knowledge from their training process, embedding it within their weights. The increasing scalability of LMs, however, poses significant challenges for understanding a model's inner workings and further for updating or correcting this embedded knowledge without the significant cost of retraining. Moreover, when using these language models for knowledge-intensive language understanding tasks, LMs have to integrate relevant context, mitigating their inherent weaknesses, such as incomplete or outdated knowledge. Nevertheless, studies indicate that LMs often ignore the provided context as it can be in conflict with the pre-existing LM's memory learned during pre-training. Conflicting knowledge can also already be present in the LM's parameters, termed intra-memory conflict. This underscores the importance of understanding the interplay between how a language model uses its parametric knowledge and the retrieved contextual knowledge. In this talk, I will aim to shed light on this important issue by presenting our research on evaluating the knowledge present in LMs, diagnostic tests that can reveal knowledge conflicts, as well as on understanding the characteristics of successfully used contextual knowledge.

Problem

• parametric knowledge
• contextual knowledge
• knowledge conflict
• language models
• knowledge integration

Innovation

• parametric knowledge
• contextual knowledge
• knowledge conflict
• intra-memory conflict
• diagnostic tests