Ross Deans Kristensen-McLachlan

Ross Deans Kristensen-McLachlan, Miceal Canavan, Márton Kardos et al.

Recent research highlights the significant potential of ChatGPT for text annotation in social science research. However, ChatGPT is a closed-source product which has major drawbacks with regards to transparency, reproducibility, cost, and data protection. Recent advances in open-source (OS) large language models (LLMs) offer an alternative without these drawbacks. Thus, it is important to evaluate the performance of OS LLMs relative to ChatGPT and standard approaches to supervised machine learning classification. We conduct a systematic comparative evaluation of the performance of a range of OS LLMs alongside ChatGPT, using both zero- and few-shot learning as well as generic and custom prompts, with results compared to supervised classification models. Using a new dataset of tweets from US news media, and focusing on simple binary text annotation tasks, we find significant variation in the performance of ChatGPT and OS models across the tasks, and that the supervised classifier using DistilBERT generally outperforms both. Given the unreliable performance of ChatGPT and the significant challenges it poses to Open Science we advise caution when using ChatGPT for substantive text annotation tasks.

Rebecca M. M. Hicke, Yuri Bizzoni, Pascale Feldkamp et al.

Focalization describes the way in which access to narrative information is restricted or controlled based on the knowledge available to knowledge of the narrator. It is encoded via a wide range of lexico-grammatical features and is subject to reader interpretation. Even trained annotators frequently disagree on correct labels, suggesting this task is both qualitatively and computationally challenging. In this work, we test how well five contemporary large language model (LLM) families and two baselines perform when annotating short literary excerpts for focalization. Despite the challenging nature of the task, we find that LLMs show comparable performance to trained human annotators, with GPT-4o achieving an average F1 of 84.79%. Further, we demonstrate that the log probabilities output by GPT-family models frequently reflect the difficulty of annotating particular excerpts. Finally, we provide a case study analyzing sixteen Stephen King novels, demonstrating the usefulness of this approach for computational literary studies and the insights gleaned from examining focalization at scale.

Mina Almasi, Ross Deans Kristensen-McLachlan

This paper investigates the potentials of Large Language Models (LLMs) as adaptive tutors in the context of second-language learning. In particular, we evaluate whether system prompting can reliably constrain LLMs to generate only text appropriate to the student's competence level. We simulate full teacher-student dialogues in Spanish using instruction-tuned, open-source LLMs ranging in size from 7B to 12B parameters. Dialogues are generated by having an LLM alternate between tutor and student roles with separate chat histories. The output from the tutor model is then used to evaluate the effectiveness of CEFR-based prompting to control text difficulty across three proficiency levels (A1, B1, C1). Our findings suggest that while system prompting can be used to constrain model outputs, prompting alone is too brittle for sustained, long-term interactional contexts - a phenomenon we term alignment drift. Our results provide insights into the feasibility of LLMs for personalized, proficiency-aligned adaptive tutors and provide a scalable method for low-cost evaluation of model performance without human participants.

Rebecca M. M. Hicke, Sil Hamilton, David Mimno et al.

Although LLM context lengths have grown, there is evidence that their ability to integrate information across long-form texts has not kept pace. We evaluate one such understanding task: generating summaries of novels. When human authors of summaries compress a story, they reveal what they consider narratively important. Therefore, by comparing human and LLM-authored summaries, we can assess whether models mirror human patterns of conceptual engagement with texts. To measure conceptual engagement, we align sentences from 150 human-written novel summaries with the specific chapters they reference. We demonstrate the difficulty of this alignment task, which indicates the complexity of summarization as a task. We then generate and align additional summaries by nine state-of-the-art LLMs for each of the 150 reference texts. Comparing the human and model-authored summaries, we find both stylistic differences between the texts and differences in how humans and LLMs distribute their focus throughout a narrative, with models emphasizing the ends of texts. Comparing human narrative engagement with model attention mechanisms suggests explanations for degraded narrative comprehension and targets for future development. We release our dataset to support future research.

Rebecca M. M. Hicke, Ross Deans Kristensen-McLachlan

Metaphors are everywhere. They appear extensively across all domains of natural language, from the most sophisticated poetry to seemingly dry academic prose. A significant body of research in the cognitive science of language argues for the existence of conceptual metaphors, the systematic structuring of one domain of experience in the language of another. Conceptual metaphors are not simply rhetorical flourishes but are crucial evidence of the role of analogical reasoning in human cognition. In this paper, we ask whether Large Language Models (LLMs) can accurately identify and explain the presence of such conceptual metaphors in natural language data. Using a novel prompting technique based on metaphor annotation guidelines, we demonstrate that LLMs are a promising tool for large-scale computational research on conceptual metaphors. Further, we show that LLMs are able to apply procedural guidelines designed for human annotators, displaying a surprising depth of linguistic knowledge.

Ross Deans Kristensen-McLachlan, Rebecca M. M. Hicke, Márton Kardos et al.

Does the People's Republic of China (PRC) interfere with European elections through ethnic Chinese diaspora media? This question forms the basis of an ongoing research project exploring how PRC narratives about European elections are represented in Chinese diaspora media, and thus the objectives of PRC news media manipulation. In order to study diaspora media efficiently and at scale, it is necessary to use techniques derived from quantitative text analysis, such as topic modelling. In this paper, we present a pipeline for studying information dynamics in Chinese media. Firstly, we present KeyNMF, a new approach to static and dynamic topic modelling using transformer-based contextual embedding models. We provide benchmark evaluations to demonstrate that our approach is competitive on a number of Chinese datasets and metrics. Secondly, we integrate KeyNMF with existing methods for describing information dynamics in complex systems. We apply this pipeline to data from five news sites, focusing on the period of time leading up to the 2024 European parliamentary elections. Our methods and results demonstrate the effectiveness of KeyNMF for studying information dynamics in Chinese media and lay groundwork for further work addressing the broader research questions.

Laurits Lyngbaek, Ross Deans Kristensen-McLachlan

Do multilingual embedding models encode a language-general representation of proficiency? We investigate this by training linear and non-linear probes on hidden-state activations from Qwen3-Embedding (0.6B, 4B, 8B) to predict CEFR proficiency levels from learner texts across nine corpora and seven languages. We compare five probing architectures against a baseline trained on surface-level text features. Under in-distribution evaluation, probes achieve strong performance ($QWK\approx0.7$), substantially outperforming the surface baseline, with middle layers consistently yielding the best predictions. However, in cross-corpus evaluation performance collapses across all probe types and model sizes. Residual analysis reveals that out-of-distribution probes converge towards predicting uniformly distributed labels, indicating that the learned mappings capture corpus-specific distributional properties (topic, language, task type, rating methodology) rather than an abstract, transferable proficiency dimension. These results suggest that current multilingual embeddings do not straightforwardly encode language-general proficiency, with implications for representation-based approaches to proficiency-adaptive language technology.

Mia Jacobsen, Ross Deans Kristensen-McLachlan

We consider the textual profiles of different fanfiction maturity ratings, how they vary across fan groups, and how this relates to reader engagement metrics. Previous studies have shown that fanfiction writing is motivated by a combination of admiration for and frustration with the fan object. These findings emerge when looking at fanfiction as a whole, as well as when it is divided into subgroups, also called fandoms. However, maturity ratings are used to indicate the intended audience of the fanfiction, as well as whether the story includes mature themes and explicit scenes. Since these ratings can be used to filter readers and writers, they can also be seen as a proxy for different reader/writer motivations and desires. We find that explicit fanfiction in particular has a distinct textual profile when compared to other maturity ratings. These findings thus nuance our understanding of reader/writer motivations in fanfiction communities, and also highlights the influence of the community norms and fan behavior more generally on these cultural products.