4 papers
Wrong Prediction, Right Answer: Recovering Evidence from Collapsed LLM Sequence Scores
Qiyao Yan, Chenpeng Wang, Liangming Pan
When a large language model fails a reasoning task, it is often assumed to lack the underlying capability. However, this conflates a genuine absence of reasoning with a late-stage…
Where Steering Signals Come From: Activation Source Selection in Activation Steering
Jiaran Ye, Lingxu Ran, Zijun Yao +5
Activation steering controls language models by adding vectors or features to hidden states at inference time, but the upstream source of these steering signals is often treated as…
Enhancing Numerical Prediction in LLMs via Smooth MMD Alignment
Zhuo Zuo, Li Yue, Wenhao Zheng +2
Despite their strong general capabilities, large language models (LLMs) often remain unreliable when outputs must be numerically precise. A key reason is the training objective: st…
HOLMES: Evaluating Higher-Order Logical Reasoning in LLMs
Yucheng Wu, Jundong Xu, Mingzhen Ju +4
Logical reasoning is essential for reliable AI, yet existing benchmarks are largely first-order-logic-centric, focusing on object-level deduction over fixed predicates. This misses…