The Year in AI Papers
The year/Labs/OpenAI

Research lab

OpenAI

Frontier model research spanning reasoning, multimodality, agents, safety, and scientific discovery.

Papers
7
Citations
468
Official code
1

7 papers from OpenAI

01

Research paper

Predicting LLM Safety Before Release by Simulating Deployment

This paper introduces deployment simulation, a method for predicting LLM safety before release by resampling the next assistant response from de-identified production conversation prefixes using a candidate model. The authors evaluate this approach across GPT-5-series deployments, finding that it produces informative estimates of post-deployment…

Marcus Williams, Hannah Sheahan, Cameron Raymond, Tomek Korbak, et al.
Published
Jul 2026
Citations
1
Code
Not linked
Read summary Original
02

arXiv.org

IH-Challenge: A Training Dataset to Improve Instruction Hierarchy on Frontier LLMs

The paper introduces IH-Challenge, a reinforcement learning (RL) training dataset designed to improve instruction hierarchy (IH) robustness in large language models (LLMs). IH defines how models prioritize system, developer, user, and tool instructions under conflict, which is key for defending against jailbreaks, system prompt extractions, and prompt…

Chuan Guo, Juan Felipe Ceron Uribe, Sicheng Zhu, Christopher A. Choquette-Choo, et al.
Published
Mar 2026
Citations
12
Code
Not linked
Read summary Original
03

arXiv.org

Reasoning Models Struggle to Control their Chains of Thought

The paper introduces CoT-Control, an evaluation suite with 14,076 instances, to measure CoT controllability—the ability of reasoning models to follow instructions that constrain their chain of thought (CoT). Across 13 frontier models, CoT controllability is significantly lower than output controllability (e.g., Claude Sonnet 4.5: 2.7% vs 61.9%).…

Chen Yueh-Han, Robert McCarthy, Bruce W. Lee, He He, et al.
Published
Mar 2026
Citations
11
Code
52 stars
Read summary Original
04

arXiv.org

Training LLMs for Honesty via Confessions

The paper proposes a method to train LLMs to produce 'confessions'—self-reports of compliance with instructions and policies—to improve honesty. Confession training adds a system message after the model's answer, requesting a structured report enumerating objectives, compliance analysis, and uncertainties. The confession reward is based solely on honesty…

Manas Joglekar, Jeremy Chen, Gabriel Wu, Jason Yosinski, et al.
Published
Dec 2025
Citations
17
Code
Not linked
Read summary Original
05

arXiv.org

Weight-sparse transformers have interpretable circuits

The paper introduces weight-sparse transformers, where most weights are zero, to improve mechanistic interpretability. By constraining the L0 norm, models learn disentangled circuits for tasks, which are pruned to isolate minimal circuits. These circuits are compact and contain neurons and residual channels corresponding to natural concepts, with…

Leo Gao, Achyuta Rajaram, Jacob Coxon, Soham V. Govande, et al.
Published
Nov 2025
Citations
37
Code
Not linked
Read summary Original
06

Robotics

GDPval: Evaluating AI Model Performance on Real-World Economically Valuable Tasks

This paper introduces GDPval, a benchmark for evaluating AI models on real-world, economically valuable tasks. It covers 44 occupations across the top 9 U.S. GDP sectors, with tasks created by industry experts averaging 14 years of experience. The benchmark includes 1,320 tasks in the full set and a 220-task gold subset, graded via human expert pairwise…

Tejal Patwardhan, Rachel Dias, Elizabeth Proehl, Grace Kim, et al.
Published
Oct 2025
Citations
108
Code
Not linked
Read summary Original
07

arXiv.org

Why Language Models Hallucinate

The paper argues that language model hallucinations arise from statistical pressures during pretraining and persist due to misaligned evaluation metrics. The authors formalize hallucinations as errors in binary classification, showing that even with error-free training data, the cross-entropy objective leads to errors. They introduce the Is-It-Valid (IIV)…

Adam Tauman Kalai, Ofir Nachum, Santosh S. Vempala, Edwin Zhang
Published
Sep 2025
Citations
282
Code
Not linked
Read summary Original