4 papers · 1 filter
Steering Large Reasoning Models towards Concise Reasoning via Flow Matching
Yawei Li, Benjamin Bergner, Yinghan Zhao +3
Large Reasoning Models (LRMs) excel at complex reasoning tasks, but their efficiency is often hampered by overly verbose outputs. Prior steering methods attempt to address this iss…
Calibrating LLMs with Information-Theoretic Evidential Deep Learning
Yawei Li, David Rügamer, Bernd Bischl +1
Fine-tuned large language models (LLMs) often exhibit overconfidence, particularly when trained on small datasets, resulting in poor calibration and inaccurate uncertainty estimate…
A Dual-Perspective Approach to Evaluating Feature Attribution Methods
Yawei Li, Yang Zhang, Kenji Kawaguchi +3
Feature attribution methods attempt to explain neural network predictions by identifying relevant features. However, establishing a cohesive framework for assessing feature attribu…
FinerCut: Finer-grained Interpretable Layer Pruning for Large Language Models
Yang Zhang, Yawei Li, Xinpeng Wang +5
Overparametrized transformer networks are the state-of-the-art architecture for Large Language Models (LLMs). However, such models contain billions of parameters making large compu…