6 papers
DualEval: Joint Model-Item Calibration for Unified LLM Evaluation
Aaron J. Li, Hao Huang, Youngmin Park +6
Current LLM evaluation relies on two complementary but often disconnected signals: static benchmarks with objective correctness labels and arena-style preference data that better r…
BenchEvolver: Frontier Task Synthesis via Solution-Centric Evolution
Yangzhen Wu, Aaron J. Li, Wenjie Ma +10
The rapid progress of frontier large language models has led to widespread benchmark saturation, limiting the ability of existing datasets to differentiate model capabilities or pr…
Green Shielding: A User-Centric Approach Towards Trustworthy AI
Aaron J. Li, Nicolas Sanchez, Hao Huang +8
Large language models (LLMs) are increasingly deployed, yet their outputs can be highly sensitive to routine, non-adversarial variation in how users phrase queries, a gap not well…
Evaluating Adversarial Robustness of Concept Representations in Sparse Autoencoders
Aaron J. Li, Suraj Srinivas, Usha Bhalla +1
Sparse autoencoders (SAEs) are commonly used to interpret the internal activations of large language models (LLMs) by mapping them to human-interpretable concept representations. W…
Certifying LLM Safety against Adversarial Prompting
Aounon Kumar, Chirag Agarwal, Suraj Srinivas +3
Large language models (LLMs) are vulnerable to adversarial attacks that add malicious tokens to an input prompt to bypass the safety guardrails of an LLM and cause it to produce ha…
More RLHF, More Trust? On The Impact of Preference Alignment On Trustworthiness
Aaron J. Li, Satyapriya Krishna, Himabindu Lakkaraju
The trustworthiness of Large Language Models (LLMs) refers to the extent to which their outputs are reliable, safe, and ethically aligned, and it has become a crucial consideration…