activity
20242026
collaborators
Showing cs.CLShow all

6 papers · 1 filter

cs.CL2026

If an LLM Were a Character, Would It Know Its Own Story? Evaluating Lifelong Learning in LLMs

Siqi Fan, Xiusheng Huang, Yiqun Yao +6

Large language models (LLMs) can carry out human-like dialogue, but unlike humans, they are stateless due to the superposition property. However, during multi-turn, multi-agent int…

cs.CL2025

Position-Aware Depth Decay Decoding (): Boosting Large Language Model Inference Efficiency

Siqi Fan, Xuezhi Fang, Xingrun Xing +3

Due to the large number of parameters, the inference phase of Large Language Models (LLMs) is resource-intensive. Unlike traditional model compression, which needs retraining, rece…

cs.CL2025

The Price of a Second Thought: On the Evaluation of Reasoning Efficiency in Large Language Models

Siqi Fan, Bowen Qin, Peng Han +3

Recent thinking models trained with reinforcement learning and backward-checking CoT often suffer from overthinking: they produce excessively long outputs even on simple problems,…

cs.CL2024

Sketch: A Toolkit for Streamlining LLM Operations

Xin Jiang, Xiang Li, Wenjia Ma +8

Large language models (LLMs) represented by GPT family have achieved remarkable success. The characteristics of LLMs lie in their ability to accommodate a wide range of tasks throu…

cs.CL2024

Open-domain Implicit Format Control for Large Language Model Generation

Yiqun Yao, Wenjia Ma, Xuezhi Fang +7

Controlling the format of outputs generated by large language models (LLMs) is a critical functionality in various applications. Current methods typically employ constrained decodi…

cs.CL2024

Not All Layers of LLMs Are Necessary During Inference

Siqi Fan, Xin Jiang, Xiang Li +6

Due to the large number of parameters, the inference phase of Large Language Models (LLMs) is resource-intensive. However, not all requests posed to LLMs are equally difficult to h…