← all papers · overview

To Trust Or Not To Trust? Enhancing Large Language Models' Situated Faithfulness To External Contexts

Abstract

Large Language Models (LLMs) are often augmented with external contexts, such as those used in retrieval-augmented generation (RAG). However, these contexts can be inaccurate or intentionally misleading, leading to conflicts with the model's internal knowledge. We argue that robust LLMs should demonstrate situated faithfulness, dynamically calibrating their trust in external information based on t

Related papers

Ranked by semantic similarity — how closely each paper's abstract matches this one (100% = near-identical topic).