activity
20242026
collaborators
Showing cs.CLShow all

5 papers · 1 filter

cs.CL2026

Gradients Must Earn Their Influence: Unifying SFT with Generalized Entropic Objectives

Zecheng Wang, Deyuan Liu, Chunshan Li +5

Standard negative log-likelihood (NLL) for Supervised Fine-Tuning (SFT) applies uniform token-level weighting. This rigidity creates a two-fold failure mode: (i) overemphasizing lo…

cs.CL2026

Beyond Confidence: The Rhythms of Reasoning in Generative Models

Deyuan Liu, Zecheng Wang, Zhanyue Qin +3

Large Language Models (LLMs) exhibit impressive capabilities yet suffer from sensitivity to slight input context variations, hampering reliability. Conventional metrics like accura…

cs.CL2026

EchoReview: Learning Peer Review from the Echoes of Scientific Citations

Yinuo Zhang, Dingcheng Huang, Haifeng Suo +9

As the volume of scientific submissions continues to grow rapidly, traditional peer review systems are facing unprecedented scalability pressures, highlighting the urgent need for…

cs.CL2025

ScEdit: Script-based Assessment of Knowledge Editing

Xinye Li, Zunwen Zheng, Qian Zhang +8

Knowledge Editing (KE) has gained increasing attention, yet current KE tasks remain relatively simple. Under current evaluation frameworks, many editing methods achieve exceptional…

cs.CL2025

LFTF: Locating First and Then Fine-Tuning for Mitigating Gender Bias in Large Language Models

Zhanyue Qin, Yue Ding, Deyuan Liu +7

Nowadays, Large Language Models (LLMs) have attracted widespread attention due to their powerful performance. However, due to the unavoidable exposure to socially biased data durin…