activity
20242026
collaborators

7 papers

cs.CL2026

Bridging Latent Reasoning and Target-Language Generation via Retrieval-Transition Heads

Shaswat Patel, Vishvesh Trivedi, Yue Han +2

Recent work has identified a subset of attention heads in Transformer as retrieval heads, which are responsible for retrieving information from the context. In this work, we first…

cs.CL2025

The Rise of Parameter Specialization for Knowledge Storage in Large Language Models

Yihuai Hong, Yiran Zhao, Wei Tang +3

Over time, a growing wave of large language models from various series has been introduced to the community. Researchers are striving to maximize the performance of language models…

cs.CL2025

Precise In-Parameter Concept Erasure in Large Language Models

Yoav Gur-Arieh, Clara Suslik, Yihuai Hong +2

Large language models (LLMs) often acquire knowledge during pretraining that is undesirable in downstream deployments, e.g., sensitive information or copyrighted content. Existing…

cs.CL2025

Intrinsic Test of Unlearning Using Parametric Knowledge Traces

Yihuai Hong, Lei Yu, Haiqin Yang +2

The task of "unlearning" certain concepts in large language models (LLMs) has attracted immense attention recently, due to its importance in mitigating undesirable model behaviours…

cs.CL2025

The Reasoning-Memorization Interplay in Language Models Is Mediated by a Single Direction

Yihuai Hong, Dian Zhou, Meng Cao +2

Large language models (LLMs) excel on a variety of reasoning benchmarks, but previous studies suggest they sometimes struggle to generalize to unseen questions, potentially due to…

cs.CL2024

Dissecting Fine-Tuning Unlearning in Large Language Models

Yihuai Hong, Yuelin Zou, Lijie Hu +3

Fine-tuning-based unlearning methods prevail for preventing targeted harmful, sensitive, or copyrighted information within large language models while preserving overall capabiliti…