Fazl Barez

Publication Activity (10 Years)

Years Active: 2021-2024
Publications (10 Years): 27

Top Topics

Language Models For Information Retrieval

Model Construction

Top Venues

Publications

Carson Denison, Monte MacDiarmid, Fazl Barez, David Duvenaud, Shauna Kravec, Samuel Marks, Nicholas Schiefer, Ryan Soklaski, Alex Tamkin, Jared Kaplan, Buck Shlegeris, Samuel R. Bowman, Ethan Perez, Evan Hubinger
Sycophancy to Subterfuge: Investigating Reward-Tampering in Large Language Models. CoRR (2024)
Michelle Lo, Shay B. Cohen, Fazl Barez
Large Language Models Relearn Removed Concepts. CoRR (2024)
Clement Neo, Shay B. Cohen, Fazl Barez
Interpreting Context Look-ups in Transformers: Investigating Attention-MLP Interactions. CoRR (2024)
Francisco Eiras, Aleksandar Petrov, Bertie Vidgen, Christian Schröder de Witt, Fabio Pizzati, Katherine Elkins, Supratik Mukhopadhyay, Adel Bibi, Aaron Purewal, Botos Csaba, Fabro Steibel, Fazel Keshtkar, Fazl Barez, Genevieve Smith, Gianluca Guadagni, Jon Chun, Jordi Cabot, Joseph Marvin Imperial, Juan Arturo Nolazco, Lori Landay, Matthew Jackson, Philip H. S. Torr, Trevor Darrell, Yong Suk Lee, Jakob N. Foerster
Risks and Opportunities of Open-Source Generative AI. CoRR (2024)
Philip Quirke, Fazl Barez
Understanding Addition in Transformers. ICLR (2024)
Nevan Wichers, Victor Tao, Riccardo Volpato, Fazl Barez
Visualizing Neural Network Imagination. CoRR (2024)
Francisco Eiras, Aleksandar Petrov, Bertie Vidgen, Christian Schröder de Witt, Fabio Pizzati, Katherine Elkins, Supratik Mukhopadhyay, Adel Bibi, Botos Csaba, Fabro Steibel, Fazl Barez, Genevieve Smith, Gianluca Guadagni, Jon Chun, Jordi Cabot, Joseph Marvin Imperial, Juan A. Nolazco-Flores, Lori Landay, Matthew Jackson, Paul Röttger, Philip H. S. Torr, Trevor Darrell, Yong Suk Lee, Jakob N. Foerster
Near to Mid-term Risks and Opportunities of Open Source Generative AI. CoRR (2024)
Philip Quirke, Clement Neo, Fazl Barez
Increasing Trust in Language Models through the Reuse of Verified Circuits. CoRR (2024)
Michelle Lo, Fazl Barez, Shay B. Cohen
Large Language Models Relearn Removed Concepts. ACL (Findings) (2024)
Evan Hubinger, Carson Denison, Jesse Mu, Mike Lambert, Meg Tong, Monte MacDiarmid, Tamera Lanham, Daniel M. Ziegler, Tim Maxwell, Newton Cheng, Adam S. Jermyn, Amanda Askell, Ansh Radhakrishnan, Cem Anil, David Duvenaud, Deep Ganguli, Fazl Barez, Jack Clark, Kamal Ndousse, Kshitij Sachan, Michael Sellitto, Mrinank Sharma, Nova DasSarma, Roger Grosse, Shauna Kravec, Yuntao Bai, Zachary Witten, Marina Favaro, Jan Brauner, Holden Karnofsky, Paul F. Christiano, Samuel R. Bowman, Logan Graham, Jared Kaplan, Sören Mindermann, Ryan Greenblatt, Buck Shlegeris, Nicholas Schiefer, Ethan Perez
Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training. CoRR (2024)
Jason Hoelscher-Obermaier, Julia Persson, Esben Kran, Ioannis Konstas, Fazl Barez
Detecting Edit Failures In Large Language Models: An Improved Specificity Benchmark. ACL (Findings) (2023)
Jason Hoelscher-Obermaier, Julia Persson, Esben Kran, Ioannis Konstas, Fazl Barez
Detecting Edit Failures In Large Language Models: An Improved Specificity Benchmark. CoRR (2023)
Albert Garde, Esben Kran, Fazl Barez
DeepDecipher: Accessing and Investigating Neuron Activation in Large Language Models. CoRR (2023)
Ondrej Bohdal, Timothy M. Hospedales, Philip H. S. Torr, Fazl Barez
Fairness in AI and Its Long-Term Implications on Society. CoRR (2023)
Alex Foote, Neel Nanda, Esben Kran, Ioannis Konstas, Shay Cohen, Fazl Barez
Neuron to Graph: Interpreting Language Model Neurons at Scale. CoRR (2023)
Philip Quirke, Fazl Barez
Understanding Addition in Transformers. CoRR (2023)
Antonio Valerio Miceli Barone, Fazl Barez, Ioannis Konstas, Shay B. Cohen
The Larger They Are, the Harder They Fail: Language Models do not Recognize Identifier Swaps in Python. CoRR (2023)
Fazl Barez, Paul Bilokon, Arthur Gervais, Nikita Lisitsyn
Exploring the Advantages of Transformers for High-Frequency Trading. CoRR (2023)
Michael Lan, Fazl Barez
Locating Cross-Task Sequence Continuation Circuits in Transformers. CoRR (2023)
Antonio Valerio Miceli Barone, Fazl Barez, Shay B. Cohen, Ioannis Konstas
The Larger they are, the Harder they Fail: Language Models do not Recognize Identifier Swaps in Python. ACL (Findings) (2023)
Kayla Matteucci, Shahar Avin, Fazl Barez, Seán Ó hÉigeartaigh
AI Systems of Concern. CoRR (2023)
Fazl Barez, Hosien Hasanbieg, Alesandro Abbate
System III: Learning with Domain Knowledge for Safety Constraints. CoRR (2023)
Fazl Barez, Philip H. S. Torr
Measuring Value Alignment. CoRR (2023)
Alex Foote, Neel Nanda, Esben Kran, Ionnis Konstas, Fazl Barez
N2G: A Scalable Approach for Quantifying Interpretable Neuron Representations in Large Language Models. CoRR (2023)
Fazl Barez, Paul Bilokon, Ruijie Xiong
Benchmarking Specialized Databases for High-frequency Data. CoRR (2023)
Luke Marks, Amir Abdullah, Luna Mendez, Rauno Arike, Philip H. S. Torr, Fazl Barez
Interpreting Reward Models in RLHF-Tuned Language Models Using Sparse Autoencoders. CoRR (2023)
Cong Wang, Tianpei Yang, Jianye Hao, Yan Zheng, Hongyao Tang, Fazl Barez, Jinyi Liu, Jiajie Peng, Haiyin Piao, Zhixiao Sun
ED2: An Environment Dynamics Decomposition Framework for World Model Construction. CoRR (2021)