1 citations · 1 across the 11 of their papers we have counts for
5 papers · 1 filter
Concept Subspaces Compute Beyond the Logit Lens: A Weights-Only Test for Locating Representations Upstream of Readout
Aojie Yuan, Zhiyuan Julian Su, Haiyue Zhang +1
A concept subspace's effect on model behavior does not establish how it relates to the output readout. We introduce a two-sided geometric diagnostic that measures an extracted subs…
SEVA: Self-Evolving Verification Agent with Process Reward for Fact Attribution
Aojie Yuan, Yi Nian, Haiyue Zhang +2
Hallucination is the reliability bottleneck for LLM-based agents, and fact attribution verifiers are the last line of defense -- yet today's verifiers emit only opaque binary label…
Hidden Error Awareness in Chain-of-Thought Reasoning: The Signal Is Diagnostic, Not Causal
Aojie Yuan, Zhiyuan Julian Su, Haiyue Zhang +2
Chain-of-thought (CoT) prompting assumes that generated reasoning reflects a model's internal computation. We show this assumption is wrong in a specific, measurable way: models in…
Beyond Language: Format-Agnostic Reasoning Subspaces in Large Language Models
Aojie Yuan, Zhiyuan Su
Large language models represent the same reasoning in vastly different surface forms -- English prose, Python code, mathematical notation -- yet whether they share a common interna…
Not All Thoughts Need HBM: Semantics-Aware Memory Hierarchy for LLM Reasoning
Aojie Yuan, Tianqi Shen, Dajun Zhang
Reasoning LLMs produce thousands of chain-of-thought tokens whose KV cache must reside in scarce GPU HBM. The dominant response -- permanently evicting low-importance tokens -- is…