Saved in:
Bibliographic Details
Main Authors: Zhang, Zhongxing, Vraga, Emily K., Huh, Jisu, Srivastava, Jaideep
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2604.06022
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915980648644608
author Zhang, Zhongxing
Vraga, Emily K.
Huh, Jisu
Srivastava, Jaideep
author_facet Zhang, Zhongxing
Vraga, Emily K.
Huh, Jisu
Srivastava, Jaideep
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2604_06022
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle BiMind: A Dual-Head Reasoning Model with Attention-Geometry Adapter for Incorrect Information Detection
Zhang, Zhongxing
Vraga, Emily K.
Huh, Jisu
Srivastava, Jaideep
Computation and Language
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.
title BiMind: A Dual-Head Reasoning Model with Attention-Geometry Adapter for Incorrect Information Detection
topic Computation and Language
url https://arxiv.org/abs/2604.06022