Tag
This paper constructs EventTyp and EventTypGold corpora to study typicality and atypicality inferences in conversation, finding that humans rely on three cues—commonsense knowledge, utterance emphasis, and snark—while LLMs struggle due to lacking commonsense knowledge about event typicality.
该论文提出一个基于回答集编程(ASP)的混合声明式框架，用于对交互式运动轨迹进行可解释的前瞻性推理，并在Argoverse 2基准上进行评估，每个预测轨迹都附带可检查的事件级假设。
CogGym is a scalable framework for comparing human and AI cognition using cognitive experiments, revealing that larger language models better mimic human reasoning but still lag behind formal benchmarks.
A paper finds that reasoning models and humans struggle with similar commonsense problems, and that chain-of-thought token count correlates with human response time when averaged across multiple runs, making it a more reliable signal of problem difficulty.
A new paper introduces SaliTrap, a benchmark of 1,145 prompts revealing that LLMs know impossible tasks but still optimize for explicit details, a failure called salience bias. Even the best models avoid traps only ~55% of the time, and awareness often doesn't prevent compliance.
This paper introduces SaliTrap, a benchmark revealing that large language models suffer from salience bias—being distracted by explicit but irrelevant conditions—in commonsense reasoning. It shows the failure is mostly due to knowledge suppression rather than absence, and that simple prompting can close the gap.
TouchThinker introduces a million-scale tactile reasoning dataset and benchmark to scale tactile commonsense reasoning to open-world settings, using action-aware representation for efficient reasoning.
This paper identifies a critical failure mode in LLM agents where they fail to update personalized memories when new evidence conflicts with prior beliefs. It introduces the STALE benchmark and a three-dimensional probing framework, revealing that even the best models achieve only 55.2% accuracy, and proposes CUPMem as a prototype for robust memory revision.