collaborators

5 papers

cs.CL2025

InfiniteICL: Breaking the Limit of Context Window Size via Long Short-term Memory Transformation

Bowen Cao, Deng Cai, Wai Lam

In-context learning (ICL) is critical for large language models (LLMs), but its effectiveness is constrained by finite context windows, particularly in ultra-long contexts. To over…

cs.CL2024

StrategyLLM: Large Language Models as Strategy Generators, Executors, Optimizers, and Evaluators for Problem Solving

Chang Gao, Haiyun Jiang, Deng Cai +2

Most existing prompting methods suffer from the issues of generalizability and consistency, as they often rely on instance-specific solutions that may not be applicable to other in…

cs.CL2024

On the Worst Prompt Performance of Large Language Models

Bowen Cao, Deng Cai, Zhisong Zhang +2

The performance of large language models (LLMs) is acutely sensitive to the phrasing of prompts, which raises significant concerns about their reliability in real-world scenarios.…

cs.CL2024

Consecutive Batch Model Editing with HooK Layers

Shuaiyi Li, Yang Deng, Deng Cai +3

As the typical retraining paradigm is unacceptably time- and resource-consuming, researchers are turning to model editing to find an effective way that supports both consecutive an…

cs.CL2024

A Thorough Examination of Decoding Methods in the Era of LLMs

Chufan Shi, Haoran Yang, Deng Cai +4

Decoding methods play an indispensable role in converting language models from next-token predictors into practical task solvers. Prior research on decoding methods, primarily focu…