Publications (13)
EnsemW2S: Enhancing Weak-to-Strong Generalization with Large Language Model Ensembles
Aakriti Agrawal, Mucong Ding, Zora Che +6
With Large Language Models (LLMs) rapidly approaching and potentially surpassing human-level performance, it has become imperative to develop approaches capable of effectively supe…
Effort-aware Fairness: Incorporating a Philosophy-informed, Human-centered Notion of Effort into Algorithmic Fairness Metrics
Tin Trung Nguyen, Jiannan Xu, Zora Che +6
Although popularized AI fairness metrics, e.g., demographic parity, have uncovered bias in AI-assisted decision-making outcomes, they do not consider how much effort one has spent…
PoisonedParrot: Subtle Data Poisoning Attacks to Elicit Copyright-Infringing Content from Large Language Models
Michael-Andrei Panaitescu-Liess, Pankayaraj Pathmanathan, Yigitcan Kaya +5
As the capabilities of large language models (LLMs) continue to expand, their usage has become increasingly prevalent. However, as reflected in numerous ongoing lawsuits regarding…
EnsemW2S: Enhancing Weak-to-Strong Generalization with Large Language Model Ensembles
Aakriti Agrawal, Mucong Ding, Zora Che +6
With Large Language Models (LLMs) rapidly approaching and potentially surpassing human-level performance, it has become imperative to develop approaches capable of effectively supe…
SAIL: Self-Improving Efficient Online Alignment of Large Language Models
Mucong Ding, Souradip Chakraborty, Vibhu Agrawal +5
Reinforcement Learning from Human Feedback (RLHF) is a key method for aligning large language models (LLMs) with human preferences. However, current offline alignment approaches li…
TutorBench: A Benchmark To Assess Tutoring Capabilities Of Large Language Models
Rakshith S Srinivasa, Zora Che, Chen Bo Calvin Zhang +11
As students increasingly adopt large language models (LLMs) as learning aids, it is crucial to build models that are adept at handling the nuances of tutoring: they need to identif…
Model Tampering Attacks Enable More Rigorous Evaluations of LLM Capabilities
Zora Che, Stephen Casper, Robert Kirk +12
Evaluations of large language model (LLM) risks and capabilities are increasingly being incorporated into AI risk management and governance frameworks. Currently, most risk evaluat…
Transferring Fairness under Distribution Shifts via Fair Consistency Regularization
Bang An, Zora Che, Mucong Ding +1
The increasing reliance on ML models in high-stakes tasks has raised a major concern on fairness violations. Although there has been a surge of work that improves algorithmic fairn…
Auction-Based Regulation for Artificial Intelligence
Marco Bornstein, Zora Che, Suhas Julapalli +3
In an era of "moving fast and breaking things", regulators have moved slowly to pick up the safety, bias, and legal debris left in the wake of broken Artificial Intelligence (AI) d…
AegisLLM: Scaling Agentic Systems for Self-Reflective Defense in LLM Security
Zikui Cai, Shayan Shabihi, Bang An +5
We introduce AegisLLM, a cooperative multi-agent defense against adversarial attacks and information leakage. In AegisLLM, a structured workflow of autonomous agents - orchestrator…
Can Watermarking Large Language Models Prevent Copyrighted Text Generation and Hide Training Data?
Michael-Andrei Panaitescu-Liess, Zora Che, Bang An +6
Large Language Models (LLMs) have demonstrated impressive capabilities in generating diverse and contextually rich text. However, concerns regarding copyright infringement arise as…
An Independent Safety Evaluation of Kimi K2.5
Zheng-Xin Yong, Parv Mahajan, Andy Wang +12
Kimi K2.5 is an open-weight LLM that rivals closed models across coding, multimodal, and agentic benchmarks, but was released without an accompanying safety evaluation. In this wor…
Best Practices for Biorisk Evaluations on Open-Weight Bio-Foundation Models
Boyi Wei, Zora Che, Nathaniel Li +10
Open-weight bio-foundation models present a dual-use dilemma. While holding great promise for accelerating scientific research and drug development, they could also enable bad acto…