Showing 2026Show all
3 papers · 1 filter
cs.CL2026
LP-SFT: Keeping Plausible Alternatives Alive in Supervised Fine-Tuning
Yueyang Wang, Baolong Bi, Shuo Lu +3
Supervised fine-tuning (SFT) is widely used to adapt pretrained language models to downstream domains, but can over-specialize the model and degrade its pre-existing capabilities.…
cs.CL2026
EdgeBench: Unveiling Scaling Laws of Learning from Real-World Environments
Deyao Zhu, Xin Zhou, Shengling Qin +44
Pretraining scaling laws reveal that model capability improves predictably with data and compute. But learning from real world environments after deployment remains far less unders…
cs.LG2026
HE-SNR: Uncovering Latent Logic via Entropy for Guiding Mid-Training on SWE-bench
Yueyang Wang, Jiawei Fu, Baolong Bi +2
SWE-bench has emerged as the premier benchmark for evaluating Large Language Models on complex software engineering tasks. While these capabilities are fundamentally acquired durin…