collaborators

7 papers

cs.LG2026

Punching Above Their Weight: Classification-Head Fine-Tuning of Tiny Language Models (TLMs) for Verifiable Multiple-Choice Tasks

Bhavesh Sood, Jaromir Savelka

We define Tiny Language Models (TLMs) as models below roughly 3B parameters that fit on mainstream consumer devices. We study how to adapt them for and use them on verifiable multi…

cs.CL2026

Towards Spec Learning: Inference-Time Alignment from Preference Pairs

Dhriti Krishnan, Tejas Goyal, Jaromir Savelka

Steering a large language model (LLM) toward a desired behavior typically relies on an iterative process of hand-crafting a prompt based on a careful inspection of the model's resp…

cs.CL2026

mmPISA-bench: Do LLMs Reason Equally Well Across 43 Languages?

Yerzhan Sapenov, Jaromir Savelka

We introduce mmPISA-bench, a compact high-quality multilingual reasoning benchmark derived from the OECD Programme for International Student Assessment (PISA). The benchmark consis…

cs.CL2026

Retrieval-Based Multi-Label Legal Annotation: Extensible, Data-Efficient and Hallucination-Free

Li Zhang, Jaromir Savelka, Kevin Ashley

Multi-label legal annotation requires assigning multiple labels from large, evolving taxonomies to long, fact-intensive documents, often under limited supervision. Parametric encod…

cs.CY2026

MCQ Difficulty Prediction via Modeling Learner Heterogeneity Using Data-Driven Cognitive Profiling

Dhriti Krishnan, Jaromir Savelka

Predicting the difficulty of multiple-choice questions (MCQs) is important for effective assessment, yet current methods typically assume a unimodal student ability distribution, o…

cs.SE2026

Changes in Coding Behavior and Performance Since the Introduction of LLMs

Yufan Zhang, Jaromir Savelka, Seth Copen Goldstein +1

The widespread availability of large language models (LLMs) has changed how students engage with coding and problem-solving. While these tools may increase student productivity, th…