AI demonstrates unprecedented reasoning capabilities, but its increasing integration into human reasoning via automated reading and summarization has provoked debate about its use for cultural interpretation. Close reading—the practice of understanding, analyzing, and critiquing cultural texts for pleasure—is a skill at the core of such interpretation, traditionally being seen as exclusive to humans. To test AI’s impact on close reading, both in terms of interpretative performance and pleasure, we conducted a preregistered randomized experiment (n = 400) investigating the impact of AI assistance by presenting single or multiple AI interpretations, on close reading poems, compared to no AI assistance. We found that single AI interpretation boosted both performance and pleasure, while multiple AI interpretations only improved performance. Further exploration revealed a trade-off: participants who heavily relied on AI showed better performance on the task but lower pleasure. Our results contribute to discussion on whether and how to calibrate AI assistance for cultural interpretation: “less is more.”

Peiqi Sui, Juan Diego Rodriguez, Philippe Laban, J. Dean Murphy, Joseph P. Dexter, Richard Jean So, Samuel Baker, Pramit Chaudhuri. Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2025.

This paper presents a systematic defense of large language model (LLM) hallucinations or 'confabulations' as a potential resource instead of a categorically negative pitfall.The standard view is that confabulations are inherently problematic and AI research should eliminate this flaw.In this paper, we argue and empirically demonstrate that measurable semantic characteristics of LLM confabulations mirror a human propensity to utilize increased narrativity as a cognitive resource for sense-making and communication.In other words, it has potential value.Specifically, we analyze popular hallucination benchmarks and reveal that hallucinated outputs display increased levels of narrativity and semantic coherence relative to veridical outputs.This finding reveals a tension in our usually dismissive understandings of confabulation.It suggests, counter-intuitively, that the tendency for LLMs to confabulate may be intimately associated with a positive capacity for coherent narrative-text generation.

Over the past decade, the field of natural language processing has developed a wide array of computational methods for reasoning about narrative, including summarization, commonsense inference, and event detection.While this work has brought an important empirical lens for examining narrative, it is by and large divorced from the large body of theoretical work on narrative within the humanities, social and cognitive sciences.In this position paper, we introduce the dominant theoretical frameworks to the NLP community, situate current research in NLP within distinct narratological traditions, and argue that linking computational work in NLP to theory opens up a range of new empirical questions that would both help advance our understanding of narrative and open up new practical applications.

Weak topic correlation across document collections with different numbers of topics in individual collections presents challenges for existing cross-collection topic models.This paper introduces two probabilistic topic models, Correlated LDA (C-LDA) and Correlated HDP (C-HDP).These address problems that can arise when analyzing large, asymmetric, and potentially weakly-related collections.Topic correlations in weakly-related collections typically lie in the tail of the topic distribution, where they would be overlooked by models unable to fit large numbers of topics.To efficiently model this long tail for large-scale analysis, our models implement a parallel sampling algorithm based on the Metropolis-Hastings and alias methods (Yuan et al., 2015).The models are first evaluated on synthetic data, generated to simulate various collection-level asymmetries.We then present a case study of modeling over 300k documents in collections of sciences and humanities research from JSTOR.