Contextual Faithfulness
Overview
Contextual faithfulness studies whether a model’s answers and reasoning are supported by the documents or other evidence it receives, especially when that evidence conflicts with its learned knowledge. Approaches include retrieval-augmented generation, preference or reinforcement-learning objectives, and inference-time decoding or attention adjustments that favor context-supported claims. Evaluation ranges from claim-level support and coverage to pairwise tests of whether answers change with context sufficiency, as well as step-level reasoning and phrase-level alignment benchmarks. A central challenge is balancing supported answers with appropriate abstention: precise systems may omit relevant facts, while retrieval quality and limited source exposure can constrain both coverage and faithfulness.
Latest papers
11 papers0 papers in the last four weeks, against 2 the four weeks before. 0.0% of all new papers.