7 papers
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…
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…
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…
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…
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…
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…