Steering Knowledge Selection Behaviours in LLMs via SAE-Based Representation Engineering

Language models are few-shot learners

Original

Tom B Brown. 2020 · 2005

Earlier work this paper cites.

What you can cram into a single vector: Probing sentence embeddings for linguistic properties

Original

Alexis Conneau, German Kruszewski, Guillaume Lample, Loïc Barrault, and Marco Baroni. 2018 · 2018

Earlier work this paper cites.

Language models as knowledge bases?

Fabio Petroni, Tim Rocktäschel, Sebastian Riedel, Patrick S. H. Lewis, Anton Bakhtin, Yuxiang Wu, and Alexander H. Miller. 2019 · 2019

Earlier work this paper cites.

Dense passage retrieval for open-domain question answering

Vladimir Karpukhin, Barlas Oguz, Sewon Min, Patrick S. H. Lewis, Ledell Wu, Sergey Edunov, Danqi Chen, and Wen-tau Yih. 2020 · 2020

Earlier work this paper cites.

Retrieval-augmented generation for knowledge-intensive nlp tasks

Patrick Lewis, Ethan Perez, Aleksandra Piktus, Fabio Petroni, Vladimir Karpukhin, Naman Goyal, Heinrich Küttler, Mike Lewis, Wen-tau Yih, Tim Rocktäschel, et al. 2020 · 2020

Earlier work this paper cites.

Null it out: Guarding protected attributes by iterative nullspace projection

Shauli Ravfogel, Yanai Elazar, Hila Gonen, Michael Twiton, and Yoav Goldberg. 2020 · 2020

Earlier work this paper cites.

A mathematical framework for transformer circuits

Nelson Elhage, Neel Nanda, Catherine Olsson, Tom Henighan, Nicholas Joseph, Ben Mann, Amanda Askell, Yuntao Bai, Anna Chen, Tom Conerly, et al. 2021 · 2021

Earlier work this paper cites.

Transformer feed-forward layers are key-value memories

Mor Geva, Roei Schuster, Jonathan Berant, and Omer Levy. 2021 · 2021

Earlier work this paper cites.

Entity-based knowledge conflicts in question answering

Shayne Longpre, Kartik Perisetla, Anthony Chen, Nikhil Ramesh, Chris DuBois, and Sameer Singh. 2021 · 2021

Earlier work this paper cites.

Transformer visualization via dictionary learning: contextualized embedding as a linear superposition of transformer factors

Zeyu Yun, Yubei Chen, Bruno Olshausen, and Yann LeCun. 2021 · 2021

Earlier work this paper cites.

Situatedqa: Incorporating extra-linguistic contexts into QA

Michael J. Q. Zhang and Eunsol Choi. 2021 · 2021

Earlier work this paper cites.

Rich knowledge sources bring complex knowledge conflicts: Recalibrating models to reflect conflicting evidence

Hung-Ting Chen, Michael J. Q. Zhang, and Eunsol Choi. 2022 · 2022

Earlier work this paper cites.

Synthetic disinformation attacks on automated fact verification systems

Yibing Du, Antoine Bosselut, and Christopher D. Manning. 2022 · 2022

Earlier work this paper cites.

Locating and editing factual associations in GPT

Kevin Meng, David Bau, Alex Andonian, and Yonatan Belinkov. 2022 · 2022

Earlier work this paper cites.

In-context learning and induction heads

Original

Catherine Olsson, Nelson Elhage, Neel Nanda, Nicholas Joseph, Nova DasSarma, Tom Henighan, Ben Mann, Amanda Askell, Yuntao Bai, Anna Chen, et al. 2022 · 2022

Earlier work this paper cites.

Extracting latent steering vectors from pretrained language models

Nishant Subramani, Nivedita Suresh, and Matthew E. Peters. 2022 · 2022

Earlier work this paper cites.

An efficient memory-augmented transformer for knowledge-intensive NLP tasks

Yuxiang Wu, Yu Zhao, Baotian Hu, Pasquale Minervini, Pontus Stenetorp, and Sebastian Riedel. 2022 · 2022

Earlier work this paper cites.

Physics of language models: Part 1, context-free grammar

Original

Zeyuan Allen-Zhu and Yuanzhi Li. 2023 · 2023

Earlier work this paper cites.

Gemini: a family of highly capable multimodal models

Original

Rohan Anil, Sebastian Borgeaud, Yonghui Wu, Jean-Baptiste Alayrac, Jiahui Yu, Radu Soricut, Johan Schalkwyk, Andrew M Dai, Anja Hauth, et al. 2023 · 2023

Earlier work this paper cites.

Towards monosemanticity: Decomposing language models with dictionary learning

Trenton Bricken, Adly Templeton, Joshua Batson, Brian Chen, Adam Jermyn, Tom Conerly, Nicholas L. Turner, Cem Anil, Carson Denison, Amanda Askell, Robert Lasenby, Yifan Wu, Shauna Kravec, Nicholas Schiefer, Tim Maxwell, Nicholas Joseph, Alex Tamkin, Karina Nguyen, Brayden McLean, Josiah E. Burke, Tristan Hume, Shan Carter, Tom Henighan, and Chris Olah. 2023 · 2023

Earlier work this paper cites.

In-context learning creates task vectors

Roee Hendel, Mor Geva, and Amir Globerson. 2023 · 2023

Cited alongside, same era.

A survey on hallucination in large language models: Principles, taxonomy, challenges, and open questions

Original

Lei Huang, Weijiang Yu, Weitao Ma, Weihong Zhong, Zhangyin Feng, Haotian Wang, Qianglong Chen, Weihua Peng, Xiaocheng Feng, Bing Qin, and Ting Liu. 2023 · 2023

Cited alongside, same era.

Shielded representations: Protecting sensitive attributes through iterative gradient-based projection

Shadi Iskander, Kira Radinsky, and Yonatan Belinkov. 2023 · 2023

Cited alongside, same era.

Mistral 7b

Original

Albert Q Jiang, Alexandre Sablayrolles, Arthur Mensch, Chris Bamford, Devendra Singh Chaplot, Diego de las Casas, Florian Bressand, Gianna Lengyel, Guillaume Lample, Lucile Saulnier, et al. 2023 · 2023

Cited alongside, same era.

Inference-time intervention: Eliciting truthful answers from a language model

Kenneth Li, Oam Patel, Fernanda B. Viégas, Hanspeter Pfister, and Martin Wattenberg. 2023 · 2023

Sparse autoencoders find highly interpretable features in language models

Robert Huben, Hoagy Cunningham, Logan Riggs, Aidan Ewart, and Lee Sharkey. 2024 · 2024

Closest in time.

Cutting off the head ends the conflict: A mechanism for interpreting and mitigating knowledge conflicts in language models

Original

Zhuoran Jin, Pengfei Cao, Hongbang Yuan, Yubo Chen, Jiexin Xu, Huaijun Li, Xiaojian Jiang, Kang Liu, and Jun Zhao. 2024 · 2024

Closest in time.

Sparse autoencoders reveal universal feature spaces across large language models

Original

Michael Lan, Philip Torr, Austin Meek, Ashkan Khakzar, David Krueger, and Fazl Barez. 2024 · 2024

Closest in time.

Gemma scope: Open sparse autoencoders everywhere all at once on gemma 2

Original

Tom Lieberum, Senthooran Rajamanoharan, Arthur Conmy, Lewis Smith, Nicolas Sonnerat, Vikrant Varma, János Kramár, Anca D. Dragan, Rohin Shah, and Neel Nanda. 2024 · 2024

Closest in time.