activity
20242026
collaborators

6 papers

cs.LG2026

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…

cs.SE2026

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…

cs.CL2026

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…

cs.LG2026

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…

cs.CL2025

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…

cs.CL2024

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…