5 papers · 1 filter
A*-Thought-V2: Efficient Latent Reasoning via Geometric Dynamics of LLM
Xiaoang Xu, Siyuan Liu, Shuo Wang +13
Chain-of-Thought (CoT) improves the reasoning ability of Large Language Models (LLMs) but incurs substantial computation and context costs. Existing methods either lose intermediat…
S-Attention:Attention-Aligned Endogenous Retrieval for Memory-Bounded Long-Context Inference
Qingsen Ma, Dianyun Wang, Yaoye Wang +7
Large language models are increasingly applied to multi-document and long-form inputs, yet long-context inference remains memory- and noise-inefficient. Key-value (KV) caching scal…
Interpretable Safety Alignment via SAE-Constructed Low-Rank Subspace Adaptation
Dianyun Wang, Qingsen Ma, Yuhu Shang +5
Safety alignment -- training large language models (LLMs) to refuse harmful requests while remaining helpful -- is critical for responsible deployment. Prior work established that…
Make an Offer They Can't Refuse: Grounding Bayesian Persuasion in Real-World Dialogues without Pre-Commitment
Buwei He, Yang Liu, Zhaowei Zhang +6
Large language models (LLMs) still struggle with strategic persuasion, largely because existing approaches either neglect information asymmetry or rely on unrealistic pre-commitmen…
From Recognition to Reasoning: Advancing Multimodal Harmful Meme Detection via Chain-of-Thought Alignment
Hexiang Gu, Qifan Yu, Yuan Liu +4
As a multimodal communication medium that integrates images and text, memes often convey implicit harmful content through metaphors, satire, and humor, making harmful meme detectio…