6 papers
Beyond State Capacity: Why Retrieval Breaks in Mamba
Nir Yarden, Amit Ben-Artzy, Roy Schwartz
Mamba models underperform Transformers on in-context retrieval. This gap is usually attributed to Mamba's fixed-size recurrent state, which loses information as the context grows.…
Rethinking the Roles of Diffusion and Decoding: Predictive-State Flows for Parallel Language Generation
Jinjin He, Xinsong Feng, Lucheng Fu +3
In continuous diffusion language models (DLMs), latents generated by the diffusion prior are mapped almost deterministically to tokens, either by a decoder or through a token embed…
Easier to Mislead Than to Correct: Harmful and Beneficial Revision in LLM Conformity
Jiaming Qu, Lucheng Fu, Yibo Hu
Large language models are increasingly used in multi-agent systems, where they see and respond to other agents' answers. A key risk is conformity: a model may abandon its own answe…
UniSD: Towards a Unified Self-Distillation Framework for Large Language Models
Yiqiao Jin, Yiyang Wang, Lucheng Fu +7
Self-distillation (SD) offers a promising path for adapting large language models (LLMs) without relying on stronger external teachers. However, SD in autoregressive LLMs remains c…
TextReg: Mitigating Prompt Distributional Overfitting via Regularized Text-Space Optimization
Lucheng Fu, Ye Yu, Yiyang Wang +4
Large language models (LLMs) are highly sensitive to the prompts used to specify task objectives and behavioral constraints. Many recent prompt optimization methods iteratively rew…
Beyond Magic Words: Sharpness-Aware Prompt Evolving for Robust Large Language Models with TARE
Guancheng Wan, Lucheng Fu, Haoxin Liu +10
The performance of Large Language Models (LLMs) hinges on carefully engineered prompts. However, prevailing prompt optimization methods, ranging from heuristic edits and reinforcem…