1 citations · 1 across the 5 of their papers we have counts for
5 papers
When and Why Do Linear Bias Probes Fail? A Geometric and Statistical Theory of Bias Detectability in Large Language Model Representations
Mo Hai, Haifeng Li
Linear probing is the standard instrument for detecting social biases in the hidden representations of large language models. Yet reported probe accuracies come almost exclusively…
Falsification-Based Verification of LLM-Generated Optimization Models: Sound Test Batteries and Their Detection Limits
Haifeng Li, Mo Hai
Large language models now translate natural-language descriptions of decision problems into solver-ready optimization models, and they fail silently. A generated model often runs a…
State-dependent error correlations shape voting thresholds in committees of AI agents
Haifeng Li, Mo Hai
The aggregation benefit of a committee of artificial intelligence (AI) agents comes from complementary information across members. Classical voting guarantees assume independent er…
CASP: Learning-Augmented Offline Approximation with Verifiable Certificates and Bounded-Loss PAC Guarantees
Haifeng Li, Mo Hai
Machine-learned predictions can speed up offline NP-hard optimization, but asking a predictor what to do amounts to asking it to solve the problem, and committing an unchecked pred…
A Multi-level Distillation based Dense Passage Retrieval Model
Haifeng Li, Mo Hai, Dong Tang
Ranker and retriever are two important components in dense passage retrieval. The retriever typically adopts a dual-encoder model, where queries and documents are separately input…