Faithfulness of Language Model Explanations

Overview

This topic asks whether a model’s explanations identify the evidence and reasoning that actually influence its answers, rather than merely offering plausible justifications afterward. Researchers test this with counterfactual prompt and evidence edits, feature ablations, activation probes and patching, and citation or verifier checks across reasoning, medical, classification, and retrieval-augmented tasks. To improve faithfulness, methods include evidence-grounded generation, structured or executable reasoning, and training with faithfulness rewards. A central challenge is that correct answers and convincing explanations do not prove causal faithfulness, while metrics often disagree and improvements can trade off against accuracy, completeness, or brevity.

Latest papers

CardsList

122 papers20 papers in the last four weeks, down 23% on the four weeks before. 0.2% of all new papers.

  1. LIFT: Likelihood-Based Intervention Faithfulness Training

    Sep 10, 2025Anand Swaroop, Maheep Chaudhary, Kevin Zhu +2CoT FaithfulnessFaithfulness of Language Model Explanations

  2. Verbosity Tradeoffs and the Impact of Scale on the Faithfulness of LLM Self-Explanations

    Mar 17, 2025Noah Y. Siegel, Nicolas Heess, Maria Perez-Ortiz +1Faithfulness of Language Model ExplanationsLLM Interpretability