Carolyn Rosé

Diya Li, Carolyn Rosé, Ao Yuan et al.

In the field of natural language processing, correction of performance assessment for chance agreement plays a crucial role in evaluating the reliability of annotations. However, there is a notable dearth of research focusing on chance correction for assessing the reliability of sequence annotation tasks, despite their widespread prevalence in the field. To address this gap, this paper introduces a novel model for generating random annotations, which serves as the foundation for estimating chance agreement in sequence annotation tasks. Utilizing the proposed randomization model and a related comparison approach, we successfully derive the analytical form of the distribution, enabling the computation of the probable location of each annotated text segment and subsequent chance agreement estimation. Through a combination simulation and corpus-based evaluation, we successfully assess its applicability and validate its accuracy and efficacy.

Manav Nitin Kapadnis, Lawanya Baghel, Atharva Naik et al.

While Multimodal Large Language Models (MLLMs) perform strongly on single-turn chart generation, their ability to support real-world exploratory data analysis remains underexplored. In practice, users iteratively refine visualizations through multi-turn interactions that require maintaining common ground, tracking prior edits, and adapting to evolving preferences. We introduce ChartEditBench, a benchmark for incremental, visually grounded chart editing via code, comprising 5,000 difficulty-controlled modification chains and a rigorously human-verified subset. Unlike prior one-shot benchmarks, ChartEditBench evaluates sustained, context-aware editing. We further propose a robust evaluation framework that mitigates limitations of LLM-as-a-Judge metrics by integrating execution-based fidelity checks, pixel-level visual similarity, and logical code verification. Experiments with state-of-the-art MLLMs reveal substantial degradation in multi-turn settings due to error accumulation and breakdowns in shared context, with strong performance on stylistic edits but frequent execution failures on data-centric transformations. ChartEditBench, establishes a challenging testbed for grounded, intent-aware multimodal programming.

Zhen Wu, Jiaxin Shi, R. Charles Murray et al.

For nearly two decades, conversational agents have played a critical role in structuring interactions in collaborative learning, shaping group dynamics, and supporting student engagement. The recent integration of large language models (LLMs) into these agents offers new possibilities for fostering critical thinking and collaborative problem solving. In this work, we begin with an open source collaboration support architecture called Bazaar and integrate an LLM-agent shell that enables introduction of LLM-empowered, real time, context sensitive collaborative support for group learning. This design and infrastructure paves the way for exploring how tailored LLM-empowered environments can reshape collaborative learning outcomes and interaction patterns.

Hyeongdon Moon, Carolyn Rosé, John Stamper

Large language models (LLMs) are widely used for tutoring, feedback generation, and content creation, but their broad pretraining makes them hard to constrain and poor substitutes for controllable learners. Educational systems often require inspectable and editable knowledge states: educators want to know what a system assumes the learner knows, and learners benefit when the system can justify actions in terms of explicit skills, misconceptions, and strategies. Inspired by cognitive architectures, we propose Cognitive Agent Compilation (CAC), a framework that uses a strong teacher LLM to compile problem-solving knowledge into an explicit target agent. CAC separates (i) knowledge representation, (ii) problem-solving policy, and (iii) verification and update rules, with the goal of making bounded problem solving more inspectable and editable in educational settings. We present an early proof of concept implemented with Small Language Models that surfaces key design trade-offs, particularly between explicit control and scalable generalization, and positions CAC as an initial step toward bounded-knowledge AI for educational applications.

Abdul Waheed, Zhen Wu, Carolyn Rosé et al.

Code data has been shown to enhance the reasoning capabilities of large language models (LLMs), but it remains unclear which aspects of code are most responsible. We investigate this question with a systematic, data-centric framework. We construct parallel instruction datasets in ten programming languages and apply controlled perturbations that selectively disrupt structural or semantic properties of code. We then finetune LLMs from five model families and eight scales on each variant and evaluate their performance on natural language, math, and code tasks. Across 3,331 experiments, our results show that LLMs are more vulnerable to structural perturbations than semantic ones, particularly on math and code tasks. Appropriate abstractions like pseudocode and flowcharts can be as effective as code, while encoding the same information with fewer tokens without adhering to original syntax can often retain or even improve performance. Remarkably, even corrupted code with misleading signals remains competitive when surface-level regularities persist. Finally, syntactic styles also shape task-specific gains with Python favoring natural language reasoning and lower-level languages such as Java and Rust favoring math. Through our systematic framework, we aim to provide insight into how different properties of code influence reasoning and inform the design of training data for enhancing LLM reasoning capabilities.

Zhen Wu, Ritam Dutt, Luke M. Breitfeller et al. · cmu

Relational reasoning lies at the core of many NLP tasks, drawing on complementary signals from text and graphs. While prior research has investigated how to leverage this dual complementarity, a detailed and systematic understanding of text-graph interplay and its effect on hybrid models remains underexplored. We take an analysis-driven approach to investigate text-graph representation complementarity via a unified architecture that supports knowledge co-distillation (CoD). We explore five tasks involving relational reasoning that differ in how text and graph structures encode the information needed to solve that task. By tracking how these dual representations evolve during training, we uncover interpretable patterns of alignment and divergence, and provide insights into when and why their integration is beneficial.

Sreecharan Sankaranarayanan, Siddharth Reddy Kandimalla, Christopher Bogart et al.

Contributing to the literature on aptitude-treatment interactions between worked examples and problem-solving, this paper addresses differential learning from the two approaches when students are positioned as domain experts learning new concepts. Our evaluation is situated in a team project that is part of an advanced software engineering course. In this course, students who possess foundational domain knowledge but are learning new concepts engage alternatively in programming followed by worked example-based reflection. They are either allowed to finish programming or are curtailed after a pre-specified time to participate in a longer worked example-based reflection. We find significant pre- to post-test learning gains in both conditions. Then, we not only find significantly more learning when students participated in longer worked example-based reflections but also a significant performance improvement on a problem-solving transfer task. These findings suggest that domain experts learning new concepts benefit more from worked example-based reflections than from problem-solving.

Denis Newman-Griffis, Jill Fain Lehman, Carolyn Rosé et al.

Natural language processing (NLP) research combines the study of universal principles, through basic science, with applied science targeting specific use cases and settings. However, the process of exchange between basic NLP and applications is often assumed to emerge naturally, resulting in many innovations going unapplied and many important questions left unstudied. We describe a new paradigm of Translational NLP, which aims to structure and facilitate the processes by which basic and applied NLP research inform one another. Translational NLP thus presents a third research paradigm, focused on understanding the challenges posed by application needs and how these challenges can drive innovation in basic science and technology design. We show that many significant advances in NLP research have emerged from the intersection of basic principles with application needs, and present a conceptual framework outlining the stakeholders and key questions in translational research. Our framework provides a roadmap for developing Translational NLP as a dedicated research area, and identifies general translational principles to facilitate exchange between basic and applied research.

Aakanksha Naik, Carolyn Rosé

We tackle the task of building supervised event trigger identification models which can generalize better across domains. Our work leverages the adversarial domain adaptation (ADA) framework to introduce domain-invariance. ADA uses adversarial training to construct representations that are predictive for trigger identification, but not predictive of the example's domain. It requires no labeled data from the target domain, making it completely unsupervised. Experiments with two domains (English literature and news) show that ADA leads to an average F1 score improvement of 3.9 on out-of-domain data. Our best performing model (BERT-A) reaches 44-49 F1 across both domains, using no labeled target data. Preliminary experiments reveal that finetuning on 1% labeled data, followed by self-training leads to substantial improvement, reaching 51.5 and 67.2 F1 on literature and news respectively.