collaborators
Showing cs.CLShow all

7 papers · 1 filter

cs.CL2026

Se-DPO: Self-Evolving Token Credit for Direct Preference Optimization

Wenxiao Zhao, Shu Wang, Ying Nian Wu

Direct Preference Optimization (DPO) aggregates token-level log-probability ratios via uniform summation, implicitly treating all tokens as contributing equally to the preference s…

cs.CL2026

A-SR: Self-Evolving Agentic LLMs for Symbolic Regression via Hierarchical Coordination

Wenxiao Zhao, Dong Liu, Kaiyi Xu +10

Symbolic regression aims to discover closed-form equations from data, but existing LLM-guided methods often rely on a unified proposal loop that compresses heterogeneous search fai…

cs.CL2026

TS-PEFT: Unveiling Token-Level Redundancy in Parameter-Efficient Fine-Tuning

Dabiao Ma, Ziming Dai, Zhimin Xin +3

Current Parameter-Efficient Fine-Tuning (PEFT) methods typically operate under an implicit assumption: Once a target module is selected, every token passing through it contributes…

cs.CL2025

Raising the Bar: Investigating the Values of Large Language Models via Generative Evolving Testing

Han Jiang, Xiaoyuan Yi, Zhihua Wei +3

Warning: Contains harmful model outputs. Despite significant advancements, the propensity of Large Language Models (LLMs) to generate harmful and unethical content poses critical c…

cs.CL2025

Latent Thought Models with Variational Bayes Inference-Time Computation

Deqian Kong, Minglu Zhao, Dehong Xu +8

We propose a novel class of language models, Latent Thought Models (LTMs), which incorporate explicit latent thought vectors that follow an explicit prior model in latent space. Th…

cs.CL2025

ToolGen: Unified Tool Retrieval and Calling via Generation

Renxi Wang, Xudong Han, Lei Ji +3

As large language models (LLMs) advance, their inability to autonomously execute tasks by directly interacting with external tools remains a critical limitation. Traditional method…