collaborators
Showing cs.CLShow all

8 papers · 1 filter

cs.CL2025

AdaMMS: Model Merging for Heterogeneous Multimodal Large Language Models with Unsupervised Coefficient Optimization

Yiyang Du, Xiaochen Wang, Chi Chen +9

Recently, model merging methods have demonstrated powerful strengths in combining abilities on various tasks from multiple Large Language Models (LLMs). While previous model mergin…

cs.CL2024

StableToolBench: Towards Stable Large-Scale Benchmarking on Tool Learning of Large Language Models

Zhicheng Guo, Sijie Cheng, Hao Wang +6

Large Language Models (LLMs) have witnessed remarkable advancements in recent years, prompting the exploration of tool learning, which integrates LLMs with external tools to addres…

cs.CL2024

Reasoning in Conversation: Solving Subjective Tasks through Dialogue Simulation for Large Language Models

Xiaolong Wang, Yile Wang, Yuanchi Zhang +4

Large Language Models (LLMs) have achieved remarkable performance in objective tasks such as open-domain question answering and mathematical reasoning, which can often be solved th…

cs.CL2024

Enhancing Multilingual Capabilities of Large Language Models through Self-Distillation from Resource-Rich Languages

Yuanchi Zhang, Yile Wang, Zijun Liu +5

While large language models (LLMs) have been pre-trained on multilingual corpora, their performance still lags behind in most languages compared to a few resource-rich languages. O…

cs.CL2024

OMGEval: An Open Multilingual Generative Evaluation Benchmark for Large Language Models

Yang Liu, Meng Xu, Shuo Wang +7

Modern large language models (LLMs) should generally benefit individuals from various cultural backgrounds around the world. However, most recent advanced generative evaluation ben…

cs.CL2024

PANDA: Preference Adaptation for Enhancing Domain-Specific Abilities of LLMs

An Liu, Zonghan Yang, Zhenhe Zhang +6

While Large language models (LLMs) have demonstrated considerable capabilities across various natural language tasks, they often fall short of the performance achieved by domain-sp…