3 papers
cs.CL2026
What Does Activation Steering Control? Attribution Across Answer Encodings and Output-Sensitive Subspaces
Zhiwei Gao, Shaowen Peng, Shoko Wakamiya +1
Activation steering is often evaluated under the answer encoding used to construct the direction. A reported gain may reflect the intended judgment or compatibility with answer ide…
cs.AI2026
When Do LLMs Apply the Wrong Law? Diagnosing LLM Failures in Temporal Legal Reasoning
Yiqian Huang, Shuyuan Zheng, Qianying Liu +6
Legal reasoning tasks such as legal judgment prediction (LJP) require identifying the temporally correct version of the law governing a case -- a capability we term temporal applic…
cs.CL2026
Can Large Language Models Imitate Human Speech for Clinical Assessment? LLM-Driven Data Augmentation for Cognitive Score Prediction
Si-Belkacem Yamine Ketir, Lenard Paulo Tamayo, Shohei Hisada +3
Accurate assessment of cognitive decline from spontaneous speech remains challenging due to limited dataset size and class imbalance. In this work, we propose a large language mode…