Large language models (LLMs) are known to memorize and recall English text from their pretraining data. However, the extent to which this ability generalizes to non-English languages or transfers across languages remains unclear. This paper investigates multilingual and cross-lingual memorization in LLMs, probing if memorized content in one language (e.g., English) can be recalled when presented in translation. To do so, we introduce , a dataset of **31.5K** aligned excerpts from 20 books in ten languages, including English originals, official translations (Vietnamese, Spanish, Turkish), and new translations in six low-resource languages (Sesotho, Yoruba, Maithili, Malagasy, Setswana, Tahitian). We evaluate memorization across model families and sizes through three tasks: (1) **direct probing**, which asks the model to identify a book’s title and author; (2) **name cloze**, which requires predicting masked character names; and (3) **prefix probing**, which involves generating continuations. We find that some LLMs consistently recall content across languages, even for texts without existing translation. GPT-4o, for example, identifies authors and titles 69.4% of the time and masked entities 6.3% of the time in newly translated excerpts. While perturbations (e.g., masking characters, shuffling words) reduce accuracy, the model’s performance remains above chance level. Our results highlight the extent of cross-lingual memorization and provide insights on the differences between the models.

Existing research on instruction following largely focuses on tasks with simple instructions and short responses. In this work, we explore multi-constraint instruction following for generating long-form text. We create Suri, a dataset with 20K human-written long-form texts paired with LLM-generated backtranslated instructions that contain multiple complex constraints. Because of prohibitive challenges associated with collecting human preference judgments on long-form texts, preference-tuning algorithms such as DPO are infeasible in our setting; thus, we propose Instructional ORPO (I-ORPO), an alignment method based on the ORPO algorithm. Instead of receiving negative feedback from dispreferred responses, I-ORPO obtains negative feedback from synthetically corrupted instructions generated by an LLM. Using Suri, we perform supervised and I-ORPO fine-tuning on Mistral-7b-Instruct-v0.2. The resulting models, Suri-SFT and Suri-I-ORPO, generate significantly longer texts (5K tokens) than base models without significant quality deterioration. Our human evaluation shows that while both SFT and I-ORPO models satisfy most constraints, Suri-I-ORPO generations are generally preferred for their coherent and informative incorporation of the constraints.

Topic modeling is a well-established technique for exploring text corpora. Conventional topic models (e.g., LDA) represent topics as bags of words that often require “reading the tea leaves” to interpret; additionally, they offer users minimal control over the formatting and specificity of resulting topics. To tackle these issues, we introduce TopicGPT, a prompt-based framework that uses large language models (LLMs) to uncover latent topics in a text collection. TopicGPT produces topics that align better with human categorizations compared to competing methods: it achieves a harmonic mean purity of 0.74 against human-annotated Wikipedia topics compared to 0.64 for the strongest baseline. Its topics are also more interpretable, dispensing with ambiguous bags of words in favor of topics with natural language labels and associated free-form descriptions. Moreover, the framework is highly adaptable, allowing users to specify constraints and modify topics without the need for model retraining. By streamlining access to high-quality and interpretable topics, TopicGPT represents a compelling, human-centered approach to topic modeling.

Understanding emotions that people express during large-scale crises helps inform policy makers and first responders about the emotional states of the population as well as provide emotional support to those who need such support. We present CovidEmo, a dataset of ~3,000 English tweets labeled with emotions and temporally distributed across 18 months. Our analyses reveal the emotional toll caused by COVID-19, and changes of the social narrative and associated emotions over time. Motivated by the time-sensitive nature of crises and the cost of large-scale annotation efforts, we examine how well large pre-trained language models generalize across domains and timeline in the task of perceived emotion prediction in the context of COVID-19. Our analyses suggest that cross-domain information transfers occur, yet there are still significant gaps. We propose semi-supervised learning as a way to bridge this gap, obtaining significantly better performance using unlabeled data from the target domain.