5 papers · 1 filter
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…
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…
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…
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…
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…