arXiv subjects

Jaromir Savelka

Publications and source records attributed to Jaromir Savelka.

At least 19 recordsLinked to original sources

arXiv2026

Unsnarling the Red Tape: Computational Infrastructure for Regulatory Systems

Regulatory complexity is increasingly recognized as an impediment to innovation, institutional responsiveness, and long-run economic growth, with regulatory accumulation estimated to reduce the U.S. GDP growth rate by nearly a full percentage point annually. This paper argues that computational approaches--including knowledge representation, artificial intelligence, natural-language processing, and cryptography--can help reduce forms of regulatory "red tape" by improving efficiency, transparency, and institutional responsiveness. We develop a framework for understanding the sources of regulatory friction and how they can be mitigated to support compliance, analysis, and reform. We further argue that effective modernization requires treating regulation not merely as legal text, but as a complex institutional and informational system that can be partially represented, analyzed, coordinated, and improved computationally while preserving legal legitimacy and procedural accountability.

cs.CY↗

arXiv2026

Personalized Assessments from Personal Artifacts

The rapid development and popularization of AI-enabled coding agents have meant software engineering students and professionals cannot be assumed to understand their own code, which risks academic integrity and professional accountability. We developed a method called Personalized Probing Puzzles ($p^3$) to evaluate students' understanding of their own code, and tested $p^3$ in a graduate-level cloud computing course. Our pilot study shows that $p^3$ can help identify potential gaps in students' understanding of their own code. The puzzles are automatically generated, asynchronously administered, and finished in minutes. Future work is needed to correlate puzzle results with code understanding and to embed $p^3$ in a professional code review process.

cs.SE↗

arXiv2026

Prompting Beats Fine-Tuning: Generative Expected Value Scoring for Statutory Term Retrieval

Legal concepts in statutes are often expressed using vague terms, and practitioners frequently turn to case law to interpret them. We study the task of ranking case-law sentences by their usefulness for explaining a concept or target statutory term, using an established dataset of 26,959 sentences covering 42 U.S. Code concepts labeled into four explanatory-value categories. We compare two families of methods: (i) supervised fine-tuning of encoder-only models (ModernBERT) and (ii) zero-shot prompting of decoder-only models. We show that across all concepts and standard NDCG cutoffs, ModernBERT largely matches earlier BERT-family baselines. In contrast, prompting decoder-only models achieves the strongest overall effectiveness, with our best system surpassing all previously reported state-of-the-art results on this task.

cs.IR↗

arXiv2026

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

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 multiple-choice tasks. We compare three LoRA-based fine-tuning paradigms (label generation, gold only, and our discriminative classification head) on a unified setup across several Qwen3 models from 0.6B to 8B and five benchmarks: HellaSwag, WinoGrande, PIQA, SciQ and ARC-C. Classification-head fine-tuning reliably outperforms label generation (+2-3%) at the 0.6B and 1.7B scales. Further, TLMs fine-tuned using the discriminative method are competitive to zero-/few-shot GPT-3 (175B), PaLM (540B) and GPT-4. The performance we report for Qwen3-0.6B and Qwen3-1.7B are SOTA on HellaSwag, WinoGrande, and PIQA.

cs.LG↗

arXiv2026

Towards Spec Learning: Inference-Time Alignment from Preference Pairs

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 responses. This is an involved, brittle, and error-prone process. Preference-based fine-tuning is a more rigorous but often prohibitively expensive solution. We propose spec learning, a framework that relies on a brief user instruction and a small set of preference judgments. These are compiled into specifications in the form of natural-language prompts for an LLM. Specifications condition LLMs at inference time, and no parameter updates to the underlying models are required. We show that the responses generated based on the compiled specifications often outperform direct preference optimization (DPO) on datasets from specialized domains whose preference signal is dense. Unlike opaque weight updates, the resulting specifications are human-readable and double as interpretable and transparent written embodiments of the preference signal that produced them.

cs.CL↗

arXiv2026

DLawBench: Evaluating LLMs Through Multi-Turn Legal Consultation

Lawyer-client consultation is a critical starting point for legal services. Effective legal assistance hinges on eliciting sufficient and truthful information from clients in order to devise strategies that best protect their interests. This task requires Large Language Models (LLMs) not only to perform robust legal reasoning, but also to strategically elicit material facts through multi-turn interactions and effectively guide clients with diverse personalities. Yet existing legal benchmarks overlook this interactive capability. To fill this gap, we introduce DLawBench, a diagnostic benchmark for real-world legal consultation. Drawing on realistic client behavior, we characterize lawyer-client interactions into four types: Cooperative, Dependent, Withdrawn, and Adversarial. Using dialogues grounded in real cases, DLawBench evaluates whether LLMs can effectively conduct legal consultation under realistic conditions. DLawBench comprises 461 cases from Chinese and U.S. law, 5,532 paired fact entries, 3,411 inquiry rubrics, and 3,348 issue-resolution rubrics, and evaluates 26 representative LLMs. Systematic experiments show substantial headroom: the best-performing model, GPT-5.5, achieves only 0.562 on consultation-grounded legal reasoning. More importantly, DLawBench exposes both sycophancy in legal consultation and a paradox: models perform worse when clients need guidance most.

cs.CL↗

arXiv2026

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

We introduce mmPISA-bench, a compact high-quality multilingual reasoning benchmark derived from the OECD Programme for International Student Assessment (PISA). The benchmark consists of 25 multiple-choice questions that require reasoning in order to be answered correctly. Each question is provided in official human translations to 43 languages and complemented with machine-translated counterparts (i.e., 2,150 data points in total). We evaluate two mainstream proprietary LLMs across languages, reasoning effort levels, and translation types in terms of their ability to answer the questions correctly. Our results show that modern LLMs can reason effectively across all evaluated languages, achieve accuracy comparable to human test-takers, with some performance variations across covered languages. We further find that machine-translated questions do not degrade accuracy relative to official human translations which suggests that high-quality machine translation (synthetic data) might often be adequate for large-scale multilingual reasoning evaluations where official translations are not available. Finally, we analyze token usage and related inference cost and find that LLMs usage in some languages is simultaneously more expensive and less accurate.

cs.CL↗

arXiv2026

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

Multi-label legal annotation requires assigning multiple labels from large, evolving taxonomies to long, fact-intensive documents, often under limited supervision. Parametric encoders typically require task-specific training and retraining when the label set changes, while prompting generative large language models becomes costly and degrades as the label space grows. We cast legal annotation as retrieval: we embed documents and label descriptions with a frozen retrieval model and predict labels via k-nearest neighbors in the embedding space, enabling updates by re-embedding and re-indexing rather than gradient-based backpropagation. Across three legal datasets (ECtHR-A, ECtHR-B, and Eurlex with 100 labels), retrieval achieves competitive accuracy and strong data efficiency; on Eurlex, Qwen-8B retrieval improves Macro-F1 from 40.41 (GPT-5.2, zero-shot) to 49.12 while reducing estimated compute by 20-30 times compared to fine-tuning. With only (N=100) training samples, retrieval nearly doubles Micro-F1 over hierarchical Legal-BERT on ECtHR-A (48.29 vs. 27.87). We also quantify a reliability failure mode of generative inference: GPT-5.2 hallucinates labels outside the provided taxonomy in 0.12-0.9% of test samples under deterministic decoding. In contrast, retrieval strictly respects defined label sets, eliminating hallucination by design. These results suggest retrieval-model-based annotators are a practical, deployable alternative for high-cardinality and rapidly changing legal label spaces.

cs.CL↗

arXiv2026

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

Predicting the difficulty of multiple-choice questions (MCQs) is important for effective assessment, yet current methods typically assume a unimodal student ability distribution, overlooking the heterogeneous nature of student misconceptions. We propose a persona-driven framework that replaces theoretical ability sampling with data-driven cognitive profiling. Using student interactions from the EEDI dataset, we identify behavioral personas via latent class analysis (LCA), then condition a large language model (LLM) to simulate response distributions for each persona. These signals are aggregated with topic context and fed into a Ridge Regression model to predict the item response theory (IRT) difficulty parameter. With five-fold cross-validation, our method improves over a recent baseline (MSE: 0.367 to 0.274; R2: 0.525 to 0.686). The discovered personas are interpretable and offer insights into why items are difficult, with potential applications to diagnostic assessment design.

cs.CY↗

arXiv2026

Changes in Coding Behavior and Performance Since the Introduction of LLMs

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, they also make it more difficult for instructors to assess students' learning and effort. In this quasi-longitudinal study, we analyze five years of student source code submissions in a graduate-level cloud computing course, focusing on an assignment that remained unchanged and examining students' behavior during the period spanning five semesters before the release of ChatGPT and five semesters after. Student coding behavior has changed significantly since Fall 2022. The length of their final submissions increased. Between consecutive submissions, average edit distances increased while average score improvement decreased, suggesting that both student productivity and learning have decreased after ChatGPT's release. Additionally, there are statistically significant correlations between these behavioral changes and their overall performance. Although we cannot definitively attribute them to LLM misuse, they are consistent with our hypothesis that some students are over-reliant on LLMs, which is negatively affecting their learning outcomes. Our findings raise an alarm around the first generation of graduates in the age of LLMs, calling upon both educators and employers to reflect on their evaluation methods for genuine expertise and productivity.

cs.SE↗

arXiv2025

Can LLMs Create Legally Relevant Summaries and Analyses of Videos?

Understanding the legally relevant factual basis of an event and conveying it through text is a key skill of legal professionals. This skill is important for preparing forms (e.g., insurance claims) or other legal documents (e.g., court claims), but often presents a challenge for laypeople. Current AI approaches aim to bridge this gap, but mostly rely on the user to articulate what has happened in text, which may be challenging for many. Here, we investigate the capability of large language models (LLMs) to understand and summarize events occurring in videos. We ask an LLM to summarize and draft legal letters, based on 120 YouTube videos showing legal issues in various domains. Overall, 71.7\% of the summaries were rated as of high or medium quality, which is a promising result, opening the door to a number of applications in e.g. access to justice.

cs.MM↗

arXiv2025

What Are the Facts? Automated Extraction of Court-Established Facts from Criminal-Court Opinions

Criminal justice administrative data contain only a limited amount of information about the committed offense. However, there is an unused source of extensive information in continental European courts' decisions: descriptions of criminal behaviors in verdicts by which offenders are found guilty. In this paper, we study the feasibility of extracting these descriptions from publicly available court decisions from Slovakia. We use two different approaches for retrieval: regular expressions and large language models (LLMs). Our baseline was a simple method employing regular expressions to identify typical words occurring before and after the description. The advanced regular expression approach further focused on "sparing" and its normalization (insertion of spaces between individual letters), typical for delineating the description. The LLM approach involved prompting the Gemini Flash 2.0 model to extract the descriptions using predefined instructions. Although the baseline identified descriptions in only 40.5% of verdicts, both methods significantly outperformed it, achieving 97% with advanced regular expressions and 98.75% with LLMs, and 99.5% when combined. Evaluation by law students showed that both advanced methods matched human annotations in about 90% of cases, compared to just 34.5% for the baseline. LLMs fully matched human-labeled descriptions in 91.75% of instances, and a combination of advanced regular expressions with LLMs reached 92%.

cs.CL↗

arXiv2025

AI Literacy for Community Colleges: Instructors' Perspectives on Scenario-Based and Interactive Approaches to Teaching AI

This research category full paper investigates how community college instructors evaluate interactive, no-code AI literacy resources designed for non-STEM learners. As artificial intelligence becomes increasingly integrated into everyday technologies, AI literacy - the ability to evaluate AI systems, communicate with them, and understand their broader impacts - has emerged as a critical skill across disciplines. Yet effective, scalable approaches for teaching these concepts in higher education remain limited, particularly for students outside STEM fields. To address this gap, we developed AI User, an interactive online curriculum that introduces core AI concepts through scenario - based activities set in real - world contexts. This study presents findings from four focus groups with instructors who engaged with AI User materials and participated in structured feedback activities. Thematic analysis revealed that instructors valued exploratory tasks that simulated real - world AI use cases and fostered experimentation, while also identifying challenges related to scaffolding, accessibility, and multi-modal support. A ranking task for instructional support materials showed a strong preference for interactive demonstrations over traditional educational materials like conceptual guides or lecture slides. These findings offer insights into instructor perspectives on making AI concepts more accessible and relevant for broad learner audiences. They also inform the design of AI literacy tools that align with diverse teaching contexts and support critical engagement with AI in higher education.

cs.CY↗

arXiv2025

"I Like That You Have to Poke Around": Instructors on How Experiential Approaches to AI Literacy Spark Inquiry and Critical Thinking

As artificial intelligence (AI) increasingly shapes decision-making across domains, there is a growing need to support AI literacy among learners beyond computer science. However, many current approaches rely on programming-heavy tools or abstract lecture-based content, limiting accessibility for non-STEM audiences. This paper presents findings from a study of AI User, a modular, web-based curriculum that teaches core AI concepts through interactive, no-code projects grounded in real-world scenarios. The curriculum includes eight projects; this study focuses on instructor feedback on Projects 5-8, which address applied topics such as natural language processing, computer vision, decision support, and responsible AI. Fifteen community college instructors participated in structured focus groups, completing the projects as learners and providing feedback through individual reflection and group discussion. Using thematic analysis, we examined how instructors evaluated the design, instructional value, and classroom applicability of these experiential activities. Findings highlight instructors' appreciation for exploratory tasks, role-based simulations, and real-world relevance, while also surfacing design trade-offs around cognitive load, guidance, and adaptability for diverse learners. This work extends prior research on AI literacy by centering instructor perspectives on teaching complex AI topics without code. It offers actionable insights for designing inclusive, experiential AI learning resources that scale across disciplines and learner backgrounds.

cs.CY↗

arXiv2025

AI Literacy Assessment Revisited: A Task-Oriented Approach Aligned with Real-world Occupations

As artificial intelligence (AI) systems become ubiquitous in professional contexts, there is an urgent need to equip workers, often with backgrounds outside of STEM, with the skills to use these tools effectively as well as responsibly, that is, to be AI literate. However, prevailing definitions and therefore assessments of AI literacy often emphasize foundational technical knowledge, such as programming, mathematics, and statistics, over practical knowledge such as interpreting model outputs, selecting tools, or identifying ethical concerns. This leaves a noticeable gap in assessing someone's AI literacy for real-world job use. We propose a work-task-oriented assessment model for AI literacy which is grounded in the competencies required for effective use of AI tools in professional settings. We describe the development of a novel AI literacy assessment instrument, and accompanying formative assessments, in the context of a US Navy robotics training program. The program included training in robotics and AI literacy, as well as a competition with practical tasks and a multiple choice scenario task meant to simulate use of AI in a job setting. We found that, as a measure of applied AI literacy, the competition's scenario task outperformed the tests we adopted from past research or developed ourselves. We argue that when training people for AI-related work, educators should consider evaluating them with instruments that emphasize highly contextualized practical skills rather than abstract technical knowledge, especially when preparing workers without technical backgrounds for AI-integrated roles.

cs.CY↗

arXiv2025

Do LLMs Truly Understand When a Precedent Is Overruled?

Large language models (LLMs) with extended context windows show promise for complex legal reasoning tasks, yet their ability to understand long legal documents remains insufficiently evaluated. Developing long-context benchmarks that capture realistic, high-stakes tasks remains a significant challenge in the field, as most existing evaluations rely on simplified synthetic tasks that fail to represent the complexity of real-world document understanding. Overruling relationships are foundational to common-law doctrine and commonly found in judicial opinions. They provide a focused and important testbed for long-document legal understanding that closely resembles what legal professionals actually do. We present an assessment of state-of-the-art LLMs on identifying overruling relationships from U.S. Supreme Court cases using a dataset of 236 case pairs. Our evaluation reveals three critical limitations: (1) era sensitivity -- the models show degraded performance on historical cases compared to modern ones, revealing fundamental temporal bias in their training; (2) shallow reasoning -- models rely on shallow logical heuristics rather than deep legal comprehension; and (3) context-dependent reasoning failures -- models produce temporally impossible relationships in complex open-ended tasks despite maintaining basic temporal awareness in simple contexts. Our work contributes a benchmark that addresses the critical gap in realistic long-context evaluation, providing an environment that mirrors the complexity and stakes of actual legal reasoning tasks.

cs.CL↗

arXiv2025

Auto-grader Feedback Utilization and Its Impacts: An Observational Study Across Five Community Colleges

Automated grading systems, or auto-graders, have become ubiquitous in programming education, and the way they generate feedback has become increasingly automated as well. However, there is insufficient evidence regarding auto-grader feedback's effectiveness in improving student learning outcomes, in a way that differentiates students who utilized the feedback and students who did not. In this study, we fill this critical gap. Specifically, we analyze students' interactions with auto-graders in an introductory Python programming course, offered at five community colleges in the United States. Our results show that students checking the feedback more frequently tend to get higher scores from their programming assignments overall. Our results also show that a submission that follows a student checking the feedback tends to receive a higher score than a submission that follows a student ignoring the feedback. Our results provide evidence on auto-grader feedback's effectiveness, encourage their increased utilization, and call for future work to continue their evaluation in this age of automation

cs.CY↗

arXiv2025

Measuring Faithfulness and Abstention: An Automated Pipeline for Evaluating LLM-Generated 3-ply Case-Based Legal Arguments

Large Language Models (LLMs) demonstrate potential in complex legal tasks like argument generation, yet their reliability remains a concern. Building upon pilot work assessing LLM generation of 3-ply legal arguments using human evaluation, this paper introduces an automated pipeline to evaluate LLM performance on this task, specifically focusing on faithfulness (absence of hallucination), factor utilization, and appropriate abstention. We define hallucination as the generation of factors not present in the input case materials and abstention as the model's ability to refrain from generating arguments when instructed and no factual basis exists. Our automated method employs an external LLM to extract factors from generated arguments and compares them against the ground-truth factors provided in the input case triples (current case and two precedent cases). We evaluated eight distinct LLMs on three tests of increasing difficulty: 1) generating a standard 3-ply argument, 2) generating an argument with swapped precedent roles, and 3) recognizing the impossibility of argument generation due to lack of shared factors and abstaining. Our findings indicate that while current LLMs achieve high accuracy (over 90%) in avoiding hallucination on viable argument generation tests (Tests 1 & 2), they often fail to utilize the full set of relevant factors present in the cases. Critically, on the abstention test (Test 3), most models failed to follow instructions to stop, instead generating spurious arguments despite the lack of common factors. This automated pipeline provides a scalable method for assessing these crucial LLM behaviors, highlighting the need for improvements in factor utilization and robust abstention capabilities before reliable deployment in legal settings. Link: https://lizhang-aiandlaw.github.io/An-Automated-Pipeline-for-Evaluating-LLM-Generated-3-ply-Case-Based-Legal-Arguments/

cs.CL↗