8 citations · 26 across the 29 of their papers we have counts for
6 papers · 1 filter
this-that-model-1.0: A typed decision model that decides in 30 ms, for a millionth of a cent
Zehua Cheng, Wei Dai, Jiahao Sun
Software delegates more of its branches to models every year: which queue a ticket enters, whether a command is safe to run, whether a claim clears without a person. What the progr…
Euston: Training Away Mathematical Sycophancy Without Losing the Mathematics
Zehua Cheng, Wei Dai, Jiahao Sun
Reasoning language models are trained to produce solutions, not to refuse them, and this bias persists when the problem they are handed is false. Asked to prove a corrupted theorem…
Imbuing Large Language Models with Bidirectional Logic for Robust Chain Repair
Zehua Cheng, Wei Dai, Jiahao Sun +1
Autoregressive chain-of-thought (CoT) reasoning in large language models (LLMs) is fundamentally forward-directed: each step conditions only on prior tokens. This unidirectional in…
CircuitSynth: Reliable Synthetic Data Generation
Zehua Cheng, Wei Dai, Jiahao Sun +1
The generation of high-fidelity synthetic data is a cornerstone of modern machine learning, yet Large Language Models (LLMs) frequently suffer from hallucinations, logical inconsis…
Provable Defense Framework for LLM Jailbreaks via Noise-Augumented Alignment
Zehua Cheng, Jianwei Yang, Wei Dai +1
Large Language Models (LLMs) remain vulnerable to adaptive jailbreaks that easily bypass empirical defenses like GCG. We propose a framework for certifiable robustness that shifts…
Collective Knowledge Graph Completion with Mutual Knowledge Distillation
Weihang Zhang, Ovidiu Serban, Jiahao Sun +1
Knowledge graph completion (KGC), the task of predicting missing information based on the existing relational data inside a knowledge graph (KG), has drawn significant attention in…