10 papers
LLM Capability Limits: Static Emergence and Dynamic Boundary Control
Yi Liu
Test-time emergence in LLM systems has a deployment boundary: additional computation can realize decisions already supported by the deployed information--execution structure, while…
How Do Answer Tokens Read Reasoning Traces? Self-Reading Patterns in Thinking LLMs for Quantitative Reasoning
Haoyang Chen, Yi Liu, Jianzhi Shao +3
Thinking LLMs produce reasoning traces before answering. Prior activation steering work mainly targets on shaping these traces. It remains less understood how answer tokens actuall…
BankerToolBench: Evaluating AI Agents in End-to-End Investment Banking Workflows
Elaine Lau, Markus Dücker, Ronak Chaudhary +24
Existing AI benchmarks lack the fidelity to assess economically meaningful progress on professional workflows. To evaluate frontier AI agents in a high-value, labor-intensive profe…
The Spectral Geometry of Thought: Phase Transitions, Instruction Reversal, Token-Level Dynamics, and Perfect Correctness Prediction in How Transformers Reason
Yi Liu
We discover that large language models exhibit \emph{spectral phase transitions} in their hidden activation spaces when engaging in reasoning versus factual recall. Through systema…
ProtSAE: Disentangling and Interpreting Protein Language Models via Semantically-Guided Sparse Autoencoders
Xiangyu Liu, Haodi Lei, Yi Liu +2
Sparse Autoencoder (SAE) has emerged as a powerful tool for mechanistic interpretability of large language models. Recent works apply SAE to protein language models (PLMs), aiming…
Answering the Unanswerable Is to Err Knowingly: Analyzing and Mitigating Abstention Failures in Large Reasoning Models
Yi Liu, Xiangyu Liu, Zequn Sun +1
Large reasoning models (LRMs) have shown remarkable progress on complex reasoning tasks. However, some questions posed to LRMs are inherently unanswerable, such as math problems la…