Goto

Collaborating Authors

 Asia



StackEval: Benchmarking LLMs in Coding Assistance

Neural Information Processing Systems

LLMs' proficiency as judges for coding tasks using a curated, human-annotated dataset, exploring their evaluation capabilities and potential biases, including whether they favor their own generated solutions. Our findings underscore the potential of these benchmarks to advance LLM development and application in coding assistance.



c7649eeb93d2fad0ced9a3b974260710-Paper-Conference.pdf

Neural Information Processing Systems

As 4, number M 100) of FedA M = 1000performs faster gradient Model trained T1 2 {0,20,40,60,80,100}, whereT1 =0 Figure 5(a), we random performs margin20%intest model.





GraphFormers

Neural Information Processing Systems

Tolearnhigh-quality representation for textual graph, techniques on natural language understanding and graph representation need to be jointly leveraged.



f187a23c3ee681ef6913f31fd6d6446b-Paper.pdf

Neural Information Processing Systems

That said, there often exist environments that resemble in structure (dynamics) yet provide more accessible rollouts (eg, unlimited in simulators).