7 papers
PERSONA: Dynamic and Compositional Inference-Time Personality Control via Activation Vector Algebra
Xiachong Feng, Liang Zhao, Weihong Zhong +5
Current methods for personality control in Large Language Models rely on static prompting or expensive fine-tuning, failing to capture the dynamic and compositional nature of human…
DLM-Scope: Mechanistic Interpretability of Diffusion Language Models via Sparse Autoencoders
Xu Wang, Bingqing Jiang, Yu Wan +3
Sparse autoencoders (SAEs) have become a standard tool for mechanistic interpretability in autoregressive large language models (LLMs), enabling researchers to extract sparse, huma…
Reasoning Path Divergence: A New Metric and Curation Strategy to Unlock LLM Diverse Thinking
Feng Ju, Zeyu Qin, Rui Min +3
While Test-Time Scaling (TTS) has proven effective in improving the reasoning ability of large language models (LLMs), low diversity in model outputs often becomes a bottleneck; th…
Teaching Language Models to Critique via Reinforcement Learning
Zhihui Xie, Jie Chen, Liyu Chen +3
Teaching large language models (LLMs) to critique and refine their outputs is crucial for building systems that can iteratively improve, yet it is fundamentally limited by the abil…
Beyond Confidence: Adaptive and Coherent Decoding for Diffusion Language Models
Kecheng Chen, Ziru Liu, Xijia Tao +7
Diffusion Language Models (DLMs) have recently achieved significant success due to their any-order generation capabilities. However, existing inference methods typically rely on lo…
FACTTRACK: Time-Aware World State Tracking in Story Outlines
Zhiheng Lyu, Kevin Yang, Lingpeng Kong +1
While accurately detecting and correcting factual contradictions in language model outputs has become increasingly important as their capabilities improve, doing so is highly chall…