arXiv subjects

Yuntao Kong

Publications and source records attributed to Yuntao Kong.

6 recordsLinked to original sources

arXiv2026

When Do LLMs Apply the Wrong Law? Diagnosing LLM Failures in Temporal Legal Reasoning

Legal reasoning tasks such as legal judgment prediction (LJP) require identifying the temporally correct version of the law governing a case -- a capability we term temporal applicable-law determination. However, whether large language models (LLMs) can reliably perform this task remains unexplored. In this paper, we construct a benchmark to evaluate LLMs on temporal applicable-law determination, and systematically investigate why they fail at temporal legal reasoning. Our experiments reveal four key findings. First, LLMs exhibit a strong bias toward applying the most recently enacted law, regardless of when the legally relevant facts occurred. Second, this bias does not stem from an inability to understand that laws have temporal scope, nor from a lack of knowledge about historical statutes. Third, we provide behavioral evidence that reinforcement-learning-shaped explicit reasoning may be a key mechanism: while improving general reasoning ability, it reduces the diversity of reasoning paths, causing models to converge on applying the current law. Fourth, this produces a counterintuitive inverse relationship: models with stronger general reasoning ability tend to perform worse on temporal legal reasoning. Our findings offer concrete guidance for future work on improving LLM performance in temporally grounded legal reasoning.

cs.AI↗

arXiv2026

GDPR Auto-Formalization with AI Agents and Human Verification

We study the overall process of automatic formalization of GDPR provisions using large language models, within a human-in-the-loop verification framework. Rather than aiming for full autonomy, we adopt a role-specialized workflow in which LLM-based AI components, operating in a multi-agent setting with iterative feedback, generate legal scenarios, formal rules, and atomic facts. This is coupled with independent verification modules which include human reviewers' assessment of representational, logical, and legal correctness. Using this approach, we construct a high-quality dataset to be used for GDPR auto-formalization, and analyze both successful and problematic cases. Our results show that structured verification and targeted human oversight are essential for reliable legal formalization, especially in the presence of legal nuance and context-sensitive reasoning.

cs.AI↗

arXiv2026

Can Legislation Be Made Machine-Readable in PROLEG?

The anticipated positive social impact of regulatory processes requires both the accuracy and efficiency of their application. Modern artificial intelligence technologies, including natural language processing and machine-assisted reasoning, hold great promise for addressing this challenge. We present a framework to address the challenge of tools for regulatory application, based on current state-of-the-art (SOTA) methods for natural language processing (large language models or LLMs) and formalization of legal reasoning (the legal representation system PROLEG). As an example, we focus on Article 6 of the European General Data Protection Regulation (GDPR). In our framework, a single LLM prompt simultaneously transforms legal text into if-then rules and a corresponding PROLEG encoding, which are then validated and refined by legal domain experts. The final output is an executable PROLEG program that can produce human-readable explanations for instances of GDPR decisions. We describe processes to support the end-to-end transformation of a segment of a regulatory document (Article 6 from GDPR), including the prompting frame to guide an LLM to "compile" natural language text to if-then rules, then to further "compile" the vetted if-then rules to PROLEG. Finally, we produce an instance that shows the PROLEG execution. We conclude by summarizing the value of this approach and note observed limitations with suggestions to further develop such technologies for capturing and deploying regulatory frameworks.

cs.CL↗

arXiv2025

Argumentative Reasoning with Language Models on Non-factorized Case Bases

In this paper, we investigate how language models can perform case-based reasoning (CBR) on non-factorized case bases. We introduce a novel framework, argumentative agentic models for case-based reasoning (AAM-CBR), which extends abstract argumentation for case-based reasoning (AA-CBR). Unlike traditional approaches that require factorization of previous cases, AAM-CBR leverages language models to determine case coverage and extract factors based on new cases. This enables factor-based reasoning without exposing or preprocessing previous cases, thus improving both flexibility and privacy. We also present initial experiments to assess AAM-CBR performance by comparing the proposed framework with a baseline that uses a single-prompt approach to incorporate both new and previous cases. The experiments are conducted based on a synthetic credit card application dataset. The result shows that AAM-CBR surpasses the baseline only when the new case contains a richer set of factors. The finding indicates that language models can handle case-based reasoning with a limited number of factors, but face challenges as the number of factors increase. Consequently, integrating symbolic reasoning with language models, as implemented in AAM-CBR, is crucial for effectively handling cases involving many factors.

cs.LO↗

arXiv2025

Online 3D Bin Packing with Fast Stability Validation and Stable Rearrangement Planning

The Online Bin Packing Problem (OBPP) is a sequential decision-making task in which each item must be placed immediately upon arrival, with no knowledge of future arrivals. Although recent deep-reinforcement-learning methods achieve superior volume utilization compared with classical heuristics, the learned policies cannot ensure the structural stability of the bin and lack mechanisms for safely reconfiguring the bin when a new item cannot be placed directly. In this work, we propose a novel framework that integrates packing policy with structural stability validation and heuristic planning to overcome these limitations. Specifically, we introduce the concept of Load Bearable Convex Polygon (LBCP), which provides a computationally efficient way to identify stable loading positions that guarantee no bin collapse. Additionally, we present Stable Rearrangement Planning (SRP), a module that rearranges existing items to accommodate new ones while maintaining overall stability. Extensive experiments on standard OBPP benchmarks demonstrate the efficiency and generalizability of our LBCP-based stability validation, as well as the superiority of SRP in finding the effort-saving rearrangement plans. Our method offers a robust and practical solution for automated packing in real-world industrial and logistics applications.

cs.RO↗

arXiv2025

BERP: A Blind Estimator of Room Parameters for Single-Channel Noisy Speech Signals

Room acoustical parameters (RAPs), room geometrical parameters (RGPs) and instantaneous occupancy level are essential metrics for parameterizing the room acoustical characteristics (RACs) of a sound field around a listener's local environment, offering comprehensive indications for various applications. Current blind estimation methods either fail to cover a broad range of real-world acoustic environments in the context of real background noise or estimate only a few RAPs and RGPs from noisy single-channel speech signals. In addition, they are limited in their ability to estimate the instantaneous occupancy level. In this paper, we propose a new universal blind estimation framework called the blind estimator of room parameters (BERP) to estimate RAPs, RGPs and occupancy level via a unified methodology. It consists of two modules: a unified room feature encoder that combines attention mechanisms with convolutional layers to learn common features across room parameters, and multiple separate parametric predictors for continuous estimation of each parameter in parallel. The combination of attention and convolutions enables the model to capture acoustic features locally and globally from speech, yielding more robust and multitask generalizable common features. Separate predictors allow the model to independently optimize for each room parameter to reduce task learning conflict and improve per-task performance. This estimation framework enables universal and efficient estimation of room parameters while maintaining satisfactory performance. To evaluate the effectiveness of the proposed framework, we compile a task-specific dataset from several publicly available datasets, including synthetic and real reverberant recordings. The results reveal that BERP achieves state-of-the-art (SOTA) performance and excellent adaptability to real-world scenarios. The code and weights are available on GitHub.

eess.AS↗