AK
Akbir Khan
cs.CLcs.LGcs.AIcs.MAcs.CVcs.CYcs.ETcs.GTstat.AP
On Valency
published · living versionsW_5uruupn8·v1 · currentpublished
Auditing language models for hidden objectives
with Samuel Marks, Johannes Treutlein, Trenton Bricken, Jack Lindsey +30
1 version
Preprints & journals
15 papers in the corpus · 2018–2025Ctrl-Z: Controlling AI Agents via Resampling2504.10374v1 · Aryan Bhatt, Cody Rushing, Adam Kaufman et al.2025 · 0 citationsarXiv
BALROG: Benchmarking Agentic LLM and VLM Reasoning On Games2411.13543v2 · Davide Paglieri, Bart\lomiej Cupia\l, Samuel Coward et al.2024 · 2 citationsarXiv
Auditing language models for hidden objectives2503.10965v2 · Samuel Marks, Johannes Treutlein, Trenton Bricken et al.2025 · 4 citationsarXivon Valency
Factorio Learning Environment2503.09617v1 · Jack Hopkins, Mart Bakler, Akbir Khan2025 · 0 citationsarXiv
Multi-Agent Risks from Advanced AI2502.14143v1 · Lewis Hammond, Alan Chan, Jesse Clifton et al.2025 · 10 citationsarXiv
Alignment faking in large language models2412.14093v2 · Ryan Greenblatt, Carson Denison, Benjamin Wright et al.2024 · 26 citationsarXivon Valency
Language Models Learn to Mislead Humans via RLHF2409.12822v3 · Jiaxin Wen, Ruiqi Zhong, Akbir Khan et al.2024 · 4 citationsarXiv
Adaptive Deployment of Untrusted LLMs Reduces Distributed Threats2411.17693v1 · Jiaxin Wen, Vivek Hebbar, Caleb Larson et al.2024 · 1 citationarXiv
Debating with More Persuasive LLMs Leads to More Truthful Answers2402.06782v4 · Akbir Khan, John Hughes, Dan Valentine et al.2024 · 11 citationsarXiv
Scaling Opponent Shaping to High Dimensional Games2312.12568v3 · Akbir Khan, Timon Willi, Newton Kwan et al.2023 · 0 citationsarXiv
Leading the Pack: N-player Opponent Shaping2312.12564v2 · Alexandra Souly, Timon Willi, Akbir Khan et al.2023 · 0 citationsarXiv
The Goldilocks of Pragmatic Understanding: Fine-Tuning Strategy Matters for Implicature Resolution by LLMs2210.14986v2 · Laura Ruis, Akbir Khan, Stella Biderman et al.2022 · 23 citationsarXiv
MAESTRO: Open-Ended Environment Design for Multi-Agent Reinforcement Learning2303.03376v1 · Mikayel Samvelyan, Akbir Khan, Michael Dennis et al.2023 · 3 citationsarXiv
Latent Racial Bias -- Evaluating Racism in Police Stop-and-Searches2005.13463v1 · Akbir Khan2020 · 0 citationsarXiv
Considering Race a Problem of Transfer Learning1812.04751v1 · Akbir Khan, Marwa Mahmoud2018 · 10 citationsarXiv
Career total: 22 works. 15 are in this corpus.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.