most citedGPT-4o System Card

164 citations · 177 across the 14 of their papers we have counts for

collaborators

15 papers

cs.AI2025★ 1 cited

Stress Testing Deliberative Alignment for Anti-Scheming Training

Bronson Schoen, Evgenia Nitishinskaya, Mikita Balesni +16

Highly capable AI systems could secretly pursue misaligned goals -- what we call "scheming". Because a scheming AI would deliberately try to hide its misaligned goals and actions,…

cs.CL2025

gpt-oss-120b & gpt-oss-20b Model Card

OpenAI, :, Sandhini Agarwal +124

We present gpt-oss-120b and gpt-oss-20b, two open-weight reasoning models that push the frontier of accuracy and inference cost. The models use an efficient mixture-of-expert trans…

cs.AI2025★ 2 cited

Chain of Thought Monitorability: A New and Fragile Opportunity for AI Safety

Tomek Korbak, Mikita Balesni, Elizabeth Barnes +38

AI systems that "think" in human language offer a unique opportunity for AI safety: we can monitor their chains of thought (CoT) for the intent to misbehave. Like all other known A…

cs.AI2025★ 8 cited

Monitoring Reasoning Models for Misbehavior and the Risks of Promoting Obfuscation

Bowen Baker, Joost Huizinga, Leo Gao +6

Mitigating reward hacking--where AI systems misbehave due to flaws or misspecifications in their learning objectives--remains a key challenge in constructing capable and aligned mo…

cs.CL2025

Considering Length Diversity in Retrieval-Augmented Summarization

Juseon-Do, Jaesung Hwang, Jingun Kwon +2

This study investigates retrieval-augmented summarization by specifically examining the impact of exemplar summary lengths under length constraints, not covered by previous work. W…

cs.CL2025

DebateBench: A Challenging Long Context Reasoning Benchmark For Large Language Models

Utkarsh Tiwari, Aryan Seth, Adi Mukherjee +3

We introduce DebateBench, a novel dataset consisting of an extensive collection of transcripts and metadata from some of the world's most prestigious competitive debates. The datas…