SOURCE-LINKED INTELLIGENCE

A Removal Based Approach to Improve LLM Faithfulness at Test-Time

arXiv · AI, language, vision and robotics · article · Sep 3, 2026 · UTC

Large language models (LLMs) are increasingly used for consequential decisions, making their explanations an important tool for auditing model behavior. Unfortunately, these explanations can be unfaithful, failing to reflect the actual reasoning underlying the model's decisions. We consider a setting in which an LLM provides both an answer and an explanation in response to a question. We identify two distinct dimensions of unfaithful explanations: incompleteness, meaning that the explanation omits factors that influence the answer, and unsoundness, meaning that the explanation cites factors th

Read original source ↗ Open in workspace

recordType

paper

region

Global