Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

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

Isabelle Augenstein

TL;DR

Research is presented on evaluating the knowledge present in LMs, diagnostic tests that can reveal knowledge conflicts, as well as on understanding the characterists of successfully used contextual knowledge.

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tasks, LMs have to integrate relevant context, mitigating their inherent weaknesses, such as incomplete or outdated knowledge.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.

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

TL;DR

Research is presented on evaluating the knowledge present in LMs, diagnostic tests that can reveal knowledge conflicts, as well as on understanding the characterists of successfully used contextual knowledge.

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.
Paper Structure (5 sections, 3 figures)

This paper contains 5 sections, 3 figures.

Table of Contents

  1. Introduction
  2. Determining what Parametric Knowledge influences a LLM’s Prediction
  3. Revealing Conflicts between Parametric and Contextual Knowledge
  4. Determining when or how RAG uses Contextual Knowledge
  5. Concluding Remarks

Figures (3)

  • Figure 1: Evaluation framework comparing Instance and Neuron Attribution methods yu-etal-2024-revealing.
  • Figure 2: Instances with varying dynamicity in the DynamicQA dataset marjanovic-etal-2024-dynamicqa.
  • Figure 3: The DRUID dataset hagstrom-etal-2025-reality in comparison with prior synthetic datasets.