Does a model's stated reason for rejecting a candidate do any work?

arXiv:2609.30151 · cs.CL, cs.AI, cs.LG · Submitted 2026-09-24 · Read on arXiv

cs.CL, cs.AI, cs.LG

Submitted: 2026-09-24

Updated: 2026-09-24

Terminology

• Consistency — 2× in this paper · explained in 3 episodes
• Decode — 2× in this paper · explained in 2 episodes
• Explainability — 2× in this paper · explained in 3 episodes
• Reinforcement Learning — 2× in this paper · explained in 4 episodes
• Accuracy — 1× in this paper · explained in 1 episode
• Benchmark — 1× in this paper · explained in 2 episodes
• Chain-of-Thought Prompting — 1× in this paper · explained in 2 episodes
• Generative AI — 1× in this paper · explained in 2 episodes
• Homogeneity — 1× in this paper · explained in 2 episodes
• Interpretability — 1× in this paper · explained in 15 episodes
• Self-consistency — 1× in this paper · explained in 2 episodes
• Tokenization — 1× in this paper · explained in 2 episodes
• Trace — 1× in this paper · explained in 2 episodes

Sources

• Explanation-Driven Counterfactual Testing for Faithfulness in Vision-Language Model Explanations
• Measuring Faithfulness in Chain-of-Thought Reasoning
• A Positive Case for Faithfulness: LLM Self-Explanations Help Predict Model Behavior
• Walk the Talk? Measuring the Faithfulness of Large Language Model Explanations
• The Disagreement Problem in Explainable Machine Learning: A Practitioner's Perspective
• "My Answer is C": First-Token Probabilities Do Not Match Text Answers in Instruction-Tuned Language Models
• Look at the Text: Instruction-Tuned Language Models are More Robust Multiple Choice Selectors than You Think
• The Probabilities Also Matter: A More Faithful Metric for Faithfulness of Free-Text Explanations in Large Language Models
• A Causal Lens for Evaluating Faithfulness Metrics
• DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
• The Out-of-Distribution Problem in Explainability and Search Methods for Feature Importance Explanations

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering