activity
20242026
collaborators
Showing cs.CLShow all

9 papers · 1 filter

cs.CL2026

Which Reasoning Trajectories Teach Students to Reason Better? A Simple Metric of Informative Alignment

Yuming Yang, Mingyoung Lai, Wanxu Zhao +13

Long chain-of-thought (CoT) trajectories provide rich supervision signals for distilling reasoning from teacher to student LLMs. However, both prior work and our experiments show t…

cs.CL2026

Analyzing the Effects of Supervised Fine-Tuning on Model Knowledge from Token and Parameter Levels

Junjie Ye, Yuming Yang, Yang Nan +7

Large language models (LLMs) acquire substantial world knowledge during pre-training, which is further shaped by post-training techniques such as supervised fine-tuning (SFT). Howe…

cs.CL2026

Pre-Trained Policy Discriminators are General Reward Models

Shihan Dou, Shichun Liu, Yuming Yang +19

We offer a novel perspective on reward modeling by formulating it as a policy discriminator, which quantifies the difference between two policies to generate a reward signal, guidi…

cs.CL2025

TL-Training: A Task-Feature-Based Framework for Training Large Language Models in Tool Use

Junjie Ye, Yilong Wu, Sixian Li +9

Large language models (LLMs) achieve remarkable advancements by leveraging tools to interact with environments, a critical step toward generalized AI. However, the standard supervi…

cs.CL2025

Measuring Data Diversity for Instruction Tuning: A Systematic Analysis and A Reliable Metric

Yuming Yang, Yang Nan, Junjie Ye +8

Data diversity is crucial for the instruction tuning of large language models. Existing studies have explored various diversity-aware data selection methods to construct high-quali…

cs.CL2025

Effective Length Extrapolation via Dimension-Wise Positional Embeddings Manipulation

Yi Lu, Wanxu Zhao, Xin Zhou +9

Large Language Models (LLMs) often struggle to process and generate coherent context when the number of input tokens exceeds the pre-trained length. Recent advancements in long-con…