paper-with-me

Papers

Beyond Hidden-Layer Manipulation: Semantically-Aware Logit Interventions for Debiasing LLMs

2025-10-25 · Wei Xia arxiv

We proposed Static and Dynamic -- two zero-shot logits-layer debiasing methods. Dynamic reduces bias by up to 70% with minimal fluency loss. Logits intervention outperforms hidden-layer approaches. We show semantic-aware logits intervention is stable and effective for debiasing aligned LLMs.

📄 PDF Abstract BibTeX arXiv:2510.23650

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

A Disentangling Invertible Interpretation Network for Explaining Latent Representations

2020-04-27 · CVPR 2020 6 · Patrick Esser, Robin Rombach, Björn Ommer

Neural networks have greatly boosted performance in computer vision by learning powerful representations of input data. The drawback of end-to-end training for maximal overall performance are black-box models whose hidde…

Image GenerationImage Manipulation

D2PPO: Diffusion Policy Policy Optimization with Dispersive Loss

2025-08-04 · Guowei Zou, Weibing Li, Hejun Wu, Yukun Qian 외 arxiv

Diffusion policies excel at robotic manipulation by naturally modeling multimodal action distributions in high-dimensional spaces. Nevertheless, diffusion policies suffer from diffusion representation collapse: semantica…

Jailbreaking Embodied LLMs via Action-level Manipulation

2026-03-02 · Xinyu Huang, Qiang Yang, Leming Shen, Zijing Ma 외 arxiv

Embodied Large Language Models (LLMs) enable AI agents to interact with the physical world through natural language instructions and actions. However, beyond the language-level risks inherent to LLMs themselves, embodied…

Spatiotemporal Hidden-State Dynamics as a Signature of Internal Reasoning in Large Language Models

2026-05-03 · Kotaro Furuya, Takahito Tanimura arxiv

Large reasoning models (LRMs) generate extended solutions, yet it remains unclear whether these traces reflect substantive internal computation or merely verbosity and overthinking. Although recent hidden-state analyses …

HANDO: Hierarchical Autonomous Navigation and Dexterous Omni-loco-manipulation

2025-10-10 · Jingyuan Sun, Chaoran Wang, Mingyu Zhang, Cui Miao 외 arxiv

Seamless loco-manipulation in unstructured environments requires robots to leverage autonomous exploration alongside whole-body control for physical interaction. In this work, we introduce HANDO (Hierarchical Autonomous …