BiMind: A Dual-Head Reasoning Model with Attention-Geometry Adapter for Incorrect Information Detection

TL;DR

BiMind is a novel dual-head reasoning model that improves incorrect information detection by disentangling internal and knowledge-augmented reasoning, introducing attention adaptation, knowledge retrieval, and uncertainty fusion strategies.

Contribution

The paper introduces BiMind, a dual-head framework with attention-geometry adaptation, knowledge retrieval, and uncertainty-aware fusion, advancing incorrect information detection methods.

Findings

BiMind outperforms existing detection approaches on public datasets.

The model provides interpretable diagnostics on knowledge contribution.

The novel VoX metric quantifies knowledge impact on reasoning.

Abstract

Incorrect information poses significant challenges by disrupting content veracity and integrity, yet most detection approaches struggle to jointly balance textual content verification with external knowledge modification under collapsed attention geometries. To address this issue, we propose a dual-head reasoning framework, BiMind, which disentangles content-internal reasoning from knowledge-augmented reasoning. In BiMind, we introduce three core innovations: (i) an attention geometry adapter that reshapes attention logits via token-conditioned offsets and mitigates attention collapse; (ii) a self-retrieval knowledge mechanism, which constructs an in-domain semantic memory through kNN retrieval and injects retrieved neighbors via feature-wise linear modulation; (iii) the uncertainty-aware fusion strategies, including entropy-gated fusion and a trainable agreement head, stabilized by a symmetric Kullback-Leibler agreement regularizer. To quantify the knowledge contributions, we define a novel metric, Value-of-eXperience (VoX), to measure instance-wise logit gains from knowledge-augmented reasoning. Experiment results on public datasets demonstrate that our BiMind model outperforms advanced detection approaches and provides interpretable diagnostics on when and why knowledge matters.