164 citations · 234 across the 12 of their papers we have counts for
12 papers
IH-Challenge: A Training Dataset to Improve Instruction Hierarchy on Frontier LLMs
Chuan Guo, Juan Felipe Ceron Uribe, Sicheng Zhu +10
Instruction hierarchy (IH) defines how LLMs prioritize system, developer, user, and tool instructions under conflict, providing a concrete, trust-ordered policy for resolving instr…
OpenAI GPT-5 System Card
Aaditya Singh, Adam Fry, Adam Perelman +483
This is the system card published alongside the OpenAI GPT-5 launch, August 2025. GPT-5 is a unified system with a smart and fast model that answers most questions, a deeper reason…
From Hard Refusals to Safe-Completions: Toward Output-Centric Safety Training
Yuan Yuan, Tina Sriskandarajah, Anna-Luisa Brakman +4
Large Language Models used in ChatGPT have traditionally been trained to learn a refusal boundary: depending on the user's intent, the model is taught to either fully comply or out…
Balancing Knowledge Delivery and Emotional Comfort in Healthcare Conversational Systems
Shang-Chi Tsai, Yun-Nung Chen
With the advancement of large language models, many dialogue systems are now capable of providing reasonable and informative responses to patients' medical conditions. However, whe…
HealthBench: Evaluating Large Language Models Towards Improved Human Health
Rahul K. Arora, Jason Wei, Rebecca Soskin Hicks +9
We present HealthBench, an open-source benchmark measuring the performance and safety of large language models in healthcare. HealthBench consists of 5,000 multi-turn conversations…
Deliberative Alignment: Reasoning Enables Safer Language Models
Melody Y. Guan, Manas Joglekar, Eric Wallace +12
As large-scale language models increasingly impact safety-critical domains, ensuring their reliable adherence to well-defined principles remains a fundamental challenge. We introdu…
Diverse and Effective Red Teaming with Auto-generated Rewards and Multi-step Reinforcement Learning
Alex Beutel, Kai Xiao, Johannes Heidecke +1
Automated red teaming can discover rare model failures and generate challenging examples that can be used for training or evaluation. However, a core challenge in automated red tea…
Rule Based Rewards for Language Model Safety
Tong Mu, Alec Helyar, Johannes Heidecke +7
Reinforcement learning based fine-tuning of large language models (LLMs) on human preferences has been shown to enhance both their capabilities and safety behavior. However, in cas…
GPT-4o System Card
OpenAI, :, Aaron Hurst +416
GPT-4o is an autoregressive omni model that accepts as input any combination of text, audio, image, and video, and generates any combination of text, audio, and image outputs. It's…
First-Person Fairness in Chatbots
Tyna Eloundou, Alex Beutel, David G. Robinson +7
Evaluating chatbot fairness is crucial given their rapid proliferation, yet typical chatbot tasks (e.g., resume writing, entertainment) diverge from the institutional decision-maki…
The Instruction Hierarchy: Training LLMs to Prioritize Privileged Instructions
Eric Wallace, Kai Xiao, Reimar Leike +3
Today's LLMs are susceptible to prompt injections, jailbreaks, and other attacks that allow adversaries to overwrite a model's original instructions with their own malicious prompt…
Multi-Group Fairness Evaluation via Conditional Value-at-Risk Testing
Lucas Monteiro Paes, Ananda Theertha Suresh, Alex Beutel +2
Machine learning (ML) models used in prediction and classification tasks may display performance disparities across population groups determined by sensitive attributes (e.g., race…