collaborators
Showing cs.CLShow all

7 papers · 1 filter

cs.CL2025

ATLAS: A High-Difficulty, Multidisciplinary Benchmark for Frontier Scientific Reasoning

Hongwei Liu, Junnan Liu, Shudong Liu +33

The rapid advancement of Large Language Models (LLMs) has led to performance saturation on many established benchmarks, questioning their ability to distinguish frontier models. Co…

cs.CL2025

NeedleBench: Evaluating LLM Retrieval and Reasoning Across Varying Information Densities

Mo Li, Songyang Zhang, Taolin Zhang +3

The capability of large language models to handle long-context information is crucial across various real-world applications. Existing evaluation methods often rely either on real-…

cs.CL2025

CompassJudger-2: Towards Generalist Judge Model via Verifiable Rewards

Taolin Zhang, Maosong Cao, Alexander Lam +2

Recently, the role of LLM-as-judge in evaluating large language models has gained prominence. However, current judge models suffer from narrow specialization and limited robustness…

cs.CL2025

Rethinking Verification for LLM Code Generation: From Generation to Testing

Zihan Ma, Taolin Zhang, Maosong Cao +5

Large language models (LLMs) have recently achieved notable success in code-generation benchmarks such as HumanEval and LiveCodeBench. However, a detailed examination reveals that…

cs.CL2025

Coding Triangle: How Does Large Language Model Understand Code?

Taolin Zhang, Zihan Ma, Maosong Cao +3

Large language models (LLMs) have achieved remarkable progress in code generation, yet their true programming competence remains underexplored. We introduce the Code Triangle frame…

cs.CL2025

Deciphering Trajectory-Aided LLM Reasoning: An Optimization Perspective

Junnan Liu, Hongwei Liu, Linchen Xiao +5

We propose a novel framework for comprehending the reasoning capabilities of large language models (LLMs) through the perspective of meta-learning. By conceptualizing reasoning tra…