The paper "Illusory Pattern Perception Drives Spurious Inference in Large Language Models" reports that large language models (LLMs) exhibit a cognitive bias similar to humans’ tendency to see patterns where none exist. By adapting classic psychological experiments to three tasks, the authors find that LLMs often over‑associate frequent positive attributes with majority groups or large organizations and are prone to constructing causal narratives from ambiguous events. Using a Sparse Autoencoder‑based interpretability framework, the study links these illusory perceptions to holistic frequency perception and analytic cognitive orientation within the models.
By Peihua Mai, Zhuoyan Shao, Xinbao Qiao, Meng Zhang, Xinyue Zhou, Yan Pang
arXiv:2601.08058v2 Announce Type: replace-cross
Abstract: Chain-of-Thought (CoT) prompting often improves the reasoning performance of large language models (LLMs), but the internal signal that trigg...
By Zhenghao He, Guangzhi Xiong, Bohan Liu, Sanchit Sinha, Aidong Zhang
Sparse autoencoders (SAEs) are proposed to extract numerous features from large language model (LLM) representations, yet explaining these features still relies primarily on external observation. This reliance leads to superficial explanations inferred from observed model behavior and computational inefficiency from collecting such behavioral evidence at scale.
arXiv:2609.01322v1 Announce Type: cross
Abstract: In many settings, studying causal questions based on text data requires adjusting for confounding information within texts. Yet there is a tradeoff i...
By Mian Zhong, Katherine A. Keith, Anjalie Field
In many settings, studying causal questions based on text data requires adjusting for confounding information within texts. Yet there is a tradeoff in constructing text representations for adjustment:...
arXiv:2604. 16197v2 Announce Type: replace Abstract: Data attribution and valuation are critical for understanding data-model synergy for Large Language Models (LLMs), yet existing gradient-based methods suffer from scalability challenges on LLMs.
By Yide Ran, Jianwen Xie, Minghui Wang, Wenjin Zheng, Denghui Zhang, Chuan Li, Zhaozhuo Xu
arXiv:2604.25866v3 Announce Type: replace
Abstract: Large language models (LLMs) are increasingly used in emotionally sensitive human-AI applications, where reliable emotion detection is essential. H...
By Bangzhao Shu, Arinjay Singh, Mai ElSherief
arXiv:2506. 23845v2 Announce Type: replace-cross Abstract: While sparse autoencoders (SAEs) have generated significant excitement, a series of negative results have added to skepticism about their usefulness.
By Kenny Peng, Rajiv Movva, Jon Kleinberg, Emma Pierson, Nikhil Garg
arXiv:2605.16339v2 Announce Type: replace
Abstract: Preference learning in large language models relies on reward models as proxies for human judgment. However, these models frequently exhibit prefer...
By Shunchang Liu, Xin Chen, Belen Martin Urcelay, Francesco Croce
arXiv:2606. 08496v1 Announce Type: cross Abstract: Although Sparse Autoencoders (SAEs) have mitigated the opacity of large language models (LLMs) by decomposing dense representations into sparse features, explaining these features still remains a central challenge.
By Jingyi He, Haiyan Zhao, Ruxue Shi, Yanguang Liu, Xin Wang, Fei Sun, Mengnan Du
arXiv:2608.22852v1 Announce Type: new
Abstract: Large language models (LLMs) are increasingly used in investment decision-making, yet prior work shows that they exhibit systematic, model-specific inv...
By Sahong Park, Suhwan Park, Hoyoung Lee, Gakyung Kwon, Wonbin Ahn, Jaewon Choi, Alejandro Lopez-Lira, Yoon Kim, Chanyeol Choi, Hyeongwoo Kong, Yongjae Lee
arXiv:2602. 09992v2 Announce Type: replace-cross Abstract: Several recent contributions have evaluated the Poverty of the Stimulus Hypothesis (PoSH) using Artificial Neural Networks (ANNs).
By Xiulin Yang, Arianna Bisazza, Nathan Schneider, Ethan Gotlieb Wilcox