6 papers
Compute as Teacher: Turning Inference Compute Into Reference-Free Supervision
Dulhan Jayalath, Shashwat Goel, Thomas Foster +5
Where do learning signals come from when there is no ground truth in post-training? We show that inference compute itself can serve as supervision. By generating parallel rollouts…
HeLa-Mem: Hebbian Learning and Associative Memory for LLM Agents
Jinchang Zhu, Jindong Li, Cheng Zhang +2
Long-term memory is a critical challenge for Large Language Model agents, as fixed context windows cannot preserve coherence across extended interactions. Existing memory systems r…
Weight Patching: Toward Source-Level Mechanistic Localization in LLMs
Chenghao Sun, Chengsheng Zhang, Guanzheng Qin +2
Mechanistic interpretability seeks to localize model behavior to the internal components that causally realize it. Prior work has advanced activation-space localization and causal…
What Characterizes Effective Reasoning? Revisiting Length, Review, and Structure of CoT
Yunzhen Feng, Julia Kempe, Cheng Zhang +2
Large reasoning models (LRMs) spend substantial test-time compute on long chain-of-thought (CoT) traces, but what *characterizes* an effective CoT remains unclear. While prior work…
HalluLens: LLM Hallucination Benchmark
Yejin Bang, Ziwei Ji, Alan Schelten +5
Large language models (LLMs) often generate responses that deviate from user input or training data, a phenomenon known as "hallucination." These hallucinations undermine user trus…
Calibrating Verbal Uncertainty as a Linear Feature to Reduce Hallucinations
Ziwei Ji, Lei Yu, Yeskendir Koishekenov +6
LLMs often adopt an assertive language style also when making false claims. Such ``overconfident hallucinations'' mislead users and erode trust. Achieving the ability to express in…