Large language models (LLMs) have demonstrated great success in various fields,
benefiting from their huge amount of parameters that store knowledge. However, LLMs still …

The rapid advancement of large language models (LLMs) has paved the way for the
development of highly capable autonomous agents. However, existing multi-agent …

In this work we systematically review the recent advancements in code processing with
language models, covering 50+ models, 30+ evaluation tasks, 170+ datasets, and 700 …

When large language models (LLMs) exceed human-level capabilities, it becomes
increasingly challenging to provide full-scale and accurate supervision for these models …

As large language models achieve impressive scores on traditional benchmarks, an
increasing number of researchers are becoming concerned about benchmark data leakage …

Most existing code Large Language Model (LLM) benchmarks, eg, EvalPlus, focus on the
code generation tasks. Namely, they contain a natural language description of a problem …

Large language models (LLMs) have demonstrated remarkable capabilities, but their
outputs can sometimes be unreliable or factually incorrect. To address this, we introduce …

Sparse Autoencoders (SAEs) have emerged as a powerful unsupervised method for
extracting sparse representations from language models, yet scalable training remains a …

Large language models (LLMs) must often respond to highly ambiguous user requests. In
such cases, the LLM's best response may be to ask a clarifying question to elicit more …

Uncertainty quantification (UQ) is a perspective approach to detecting Large Language
Model (LLM) hallucinations and low quality output. In this work, we address one of the …