Harnessing Reasoning Trajectories for Hallucination Detection via Answer-agreement Representation Shaping
For researchers and practitioners deploying large reasoning models, this work provides a method to detect hallucinations without human annotations, addressing a key reliability bottleneck.
The paper tackles hallucination detection in large reasoning models by proposing Answer-agreement Representation Shaping (ARS), which learns detection-friendly representations via latent interventions that perturb trace-boundary embeddings and label perturbations by answer agreement. ARS consistently improves detection and achieves substantial gains over strong baselines.
Large reasoning models (LRMs) often generate long, seemingly coherent reasoning traces yet still produce incorrect answers, making hallucination detection challenging. Although trajectories contain useful signals, directly using trace text or vanilla hidden states for detection is brittle: traces vary in form and detectors can overfit to superficial patterns rather than answer validity. We introduce Answer-agreement Representation Shaping (ARS), which learns detection-friendly trace-conditioned representations by explicitly encoding answer stability. ARS generates counterfactual answers through small latent interventions, specifically, perturbing the trace-boundary embedding, and labels each perturbation by whether the resulting answer agrees with the original. It then learns representations that bring answer-agreeing states together and separate answer-disagreeing ones, exposing latent instability indicative of hallucination risk. The shaped embeddings are plug-and-play with existing embedding-based detectors and require no human annotations during training. Experiments demonstrate that ARS consistently improves detection and achieves substantial gains over strong baselines. Code is available at: https://github.com/radiolab-ntu/ars_icml2026.