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

arXiv: https://arxiv.org/abs/2604.06022 · HTML: https://mlsanity.com/paper/2604.06022/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Test-time compute and efficient thinking, one of 17 directions in LLM reasoning.
- Builds on 9 of its 72 references that are in the map.
- First posted on arXiv 7 Apr 2026.

## Placed in

- LLM reasoning / [Test-time compute and efficient thinking](https://mlsanity.com/lr/test-time-compute-and-efficient-thinking/)

## Builds on (most cited first, 9 of 9)

- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [DeBERTa: Decoding-enhanced BERT with Disentangled Attention](https://mlsanity.com/paper/2006.03654/) (2020)
- [Graph Convolutional Networks for Text Classification](https://mlsanity.com/paper/1809.05679/) (2018)
- [MM-COVID: A Multilingual and Multimodal Data Repository for Combating COVID-19 Disinformation](https://mlsanity.com/paper/2011.04088/) (2020)
- [Network-based Fake News Detection: A Pattern-driven Approach](https://mlsanity.com/paper/1906.04210/) (2019)
- [Contextual Integrity in LLMs via Reasoning and Reinforcement Learning](https://mlsanity.com/paper/2506.04245/) (2025)
- [Explainable Tsetlin Machine framework for fake news detection with credibility score assessment](https://mlsanity.com/paper/2105.09114/) (2021)
- [Combining Machine Learning with Knowledge Engineering to detect Fake News in Social Networks-a survey](https://mlsanity.com/paper/2201.08032/) (2022)

## Built on by (most cited first, 1 of 1)

- [ActorMind: Emulating Human Actor Reasoning for Speech Role-Playing](https://mlsanity.com/paper/2604.11103/) (2026)

## Abstract (arXiv)

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.