paper-with-me

홈 › Papers

Empirical Study on Updating Key-Value Memories in Transformer Feed-forward Layers

2024-02-19 · Zihan Qiu, Zeyu Huang, Youcheng Huang, Jie Fu

The feed-forward networks (FFNs) in transformers are recognized as a group of key-value neural memories to restore abstract high-level knowledge. In this work, we conduct an empirical ablation study on updating keys (the 1st layer in the FFNs layer) or values (the 2nd layer in the FFNs layer). We compare those two methods in various knowledge editing and fine-tuning tasks of large language models to draw insights to understand FFNs further. Code is available at $\href{https://github.com/qiuzh20/Tuning-keys-v.s.-values}{this\,repo}$.

📄 PDF Abstract BibTeX arXiv:2402.12233

Code (1)

qiuzh20/tuning-keys-v.s.-values 공식 구현 pytorch

Tasks

knowledge editing

Similar Papers 제목 키워드 기반

Mass-Editing Memory in a Transformer

2022-10-13 · Kevin Meng, Arnab Sen Sharma, Alex Andonian, Yonatan Belinkov 외

Recent work has shown exciting promise in updating large language models with new memories, so as to replace obsolete information or add specialized knowledge. However, this line of work is predominantly limited to updat…

Language ModelingLanguage Modelling

Associative Memories Based on Multiple-Valued Sparse Clustered Networks

2014-02-03 · Hooman Jarollahi, Naoya Onizawa, Takahiro Hanyu, Warren J. Gross

Associative memories are structures that store data patterns and retrieve them given partial inputs. Sparse Clustered Networks (SCNs) are recently-introduced binary-weighted associative memories that significantly improv…

Retrieval

Transformer Feed-Forward Layers Are Key-Value Memories

2020-12-29 · EMNLP 2021 11 · Mor Geva, Roei Schuster, Jonathan Berant, Omer Levy

Feed-forward layers constitute two-thirds of a transformer model's parameters, yet their role in the network remains under-explored. We show that feed-forward layers in transformer-based language models operate as key-va…

A Study on ReLU and Softmax in Transformer

2023-02-13 · Kai Shen, Junliang Guo, Xu Tan, Siliang Tang 외

The Transformer architecture consists of self-attention and feed-forward networks (FFNs) which can be viewed as key-value memories according to previous works. However, FFN and traditional memory utilize different activa…

Document Translation

Experience Makes Skillful: Enabling Generalizable Medical Agent Reasoning via Self-Evolving Skill Memory

2026-06-08 · Haoran Sun, Wenjie Li, Yujie Zhang, Zekai Lin 외 arxiv

Medical agent systems are increasingly expected to support interactive clinical decision making rather than only static question answering. In such settings, effective agents must reuse prior experience across evolving c…

Question AnsweringDecision Making