Joe Benton

Identifiers

• name variant Joe Benton 0.60 · backfill

Papers (8)

1. Diffuse AI Control on Fuzzy Tasks cs.LG · 2026 · author #4
2. Faithfulness as Information Flow: Evaluating and Training Faithful Chain-of-Thought Reasoning cs.LG · 2026 · author #2
3. SLEIGHT-Bench: A Benchmark of Evasion Attacks Against Agent Monitors cs.CR · 2026 · author #5
4. Efficiently Aligning Language Models with Online Natural Language Feedback cs.LG · 2026 · author #2
5. Removing Sandbagging in LLMs by Training with Weak Supervision cs.LG · 2026 · author #4
6. Chain of Thought Monitorability: A New and Fragile Opportunity for AI Safety cs.AI · 2025 · author #5
7. Reasoning Models Don't Always Say What They Think cs.CL · 2025 · author #2
8. Constitutional Classifiers: Defending against Universal Jailbreaks across Thousands of Hours of Red Teaming cs.CL · 2025 · author #13

Mentions

• 2606.08892 #4 · arxiv_oai · confidence 0.70 Joe Benton
• 2605.04356 #2 · arxiv_oai · confidence 0.70 Joe Benton
• 2605.24286 #2 · arxiv_oai · confidence 0.70 Joe Benton
• 2507.11473 #5 · arxiv_oai · confidence 0.70 Joe Benton
• 2605.16626 #5 · arxiv_oai · confidence 0.70 Joe Benton
• 2501.18837 #13 · arxiv_oai · confidence 0.70 Joe Benton

Frequent Coauthors

• Ethan Perez 3 shared papers
• Fabien Roger 3 shared papers
• Jan Leike 2 shared papers
• Jared Kaplan 2 shared papers
• Samuel R. Bowman 2 shared papers
• Vivek Hebbar 2 shared papers
• Vlad Mikulik 2 shared papers
• Alan Cooney 1 shared papers
• Aleksander M\k{a}dry 1 shared papers
• Alex Silverstein 1 shared papers
• Allan Dafoe 1 shared papers
• Alwin Peng 1 shared papers
• Amanda Askell 1 shared papers
• Anca Dragan 1 shared papers
• Andy Dau 1 shared papers
• Anjali Gopal 1 shared papers
• Ansh Radhakrishnan 1 shared papers
• Arushi Somani 1 shared papers
• Bowen Baker 1 shared papers
• Buck Shlegeris 1 shared papers