3 papers
cs.CR2026
Defenses & Enablers For Skill Injection Attacks on Terminal Based Agents
Yoshinari Fujinuma, Varun Gangal, Traian Rebedea +4
Large language model (LLM) agents increasingly rely on reusable skills i.e. documents describing task-specific procedures. However, this introduces a new attack surface for agents…
cs.CL2026
Contrastive Decoding Mitigates Score Range Bias in LLM-as-a-Judge
Yoshinari Fujinuma
Large Language Models (LLMs) are commonly used as evaluators in various applications, but the reliability of the outcomes remains a challenge. One such challenge is using LLMs-as-j…
cs.CL2026
Unlocking Prompt Infilling Capability for Diffusion Language Models
Yoshinari Fujinuma, Keisuke Sakaguchi
Masked diffusion language models (dLMs) generate text through bidirectional denoising, yet this capability remains locked for infilling prompts. This limitation is an artifact of t…