Ken Satoh

Ha Thanh Nguyen, Randy Goebel, Francesca Toni et al.

Negation is a fundamental aspect of natural language, playing a critical role in communication and comprehension. Our study assesses the negation detection performance of Generative Pre-trained Transformer (GPT) models, specifically GPT-2, GPT-3, GPT-3.5, and GPT-4. We focus on the identification of negation in natural language using a zero-shot prediction approach applied to our custom xNot360 dataset. Our approach examines sentence pairs labeled to indicate whether the second sentence negates the first. Our findings expose a considerable performance disparity among the GPT models, with GPT-4 surpassing its counterparts and GPT-3.5 displaying a marked performance reduction. The overall proficiency of the GPT models in negation detection remains relatively modest, indicating that this task pushes the boundaries of their natural language understanding capabilities. We not only highlight the constraints of GPT models in handling negation but also emphasize the importance of logical reliability in high-stakes domains such as healthcare, science, and law.

Vu Tran, Minh Le Nguyen, Satoshi Tojo et al.

We present our method for tackling a legal case retrieval task by introducing our method of encoding documents by summarizing them into continuous vector space via our phrase scoring framework utilizing deep neural networks. On the other hand, we explore the benefits from combining lexical features and latent features generated with neural networks. Our experiments show that lexical features and latent features generated with neural networks complement each other to improve the retrieval system performance. Furthermore, our experimental results suggest the importance of case summarization in different aspects: using provided summaries and performing encoded summarization. Our approach achieved F1 of 65.6% and 57.6% on the experimental datasets of legal case retrieval tasks.

Jieying Xue, Phuong Minh Nguyen, Ha Thanh Nguyen et al.

This work aims to improve the generalization of logic-based legal reasoning systems by integrating recent advances in NLP with legal-domain adaptive few-shot learning techniques using LLMs. Existing logic-based legal reasoning pipelines typically rely on fine-tuned models to map natural-language legal cases into logical formulas before forwarding them to a symbolic reasoner. However, such approaches are heavily constrained by the scarcity of high-quality annotated training data. To address this limitation, we propose a novel LLM-based legal reasoning framework that enables effective in-context learning through retrieval-augmented generation. Specifically, we introduce Legal2LogicICL, a few-shot retrieval framework that balances diversity and similarity of exemplars at both the latent semantic representation level and the legal text structure level. In addition, our method explicitly accounts for legal structure by mitigating entity-induced retrieval bias in legal texts, where lengthy and highly specific entity mentions often dominate semantic representations and obscure legally meaningful reasoning patterns. Our Legal2LogicICL constructs informative and robust few-shot demonstrations, leading to accurate and stable logical rule generation without requiring additional training. In addition, we construct a new dataset, named Legal2Proleg, which is annotated with alignments between legal cases and PROLEG logical formulas to support the evaluation of legal semantic parsing. Experimental results on both open-source and proprietary LLMs demonstrate that our approach significantly improves accuracy, stability, and generalization in transforming natural-language legal case descriptions into logical representations, highlighting its effectiveness for interpretable and reliable legal reasoning. Our code is available at https://github.com/yingjie7/Legal2LogicICL.

Ha-Thanh Nguyen, Randy Goebel, Francesca Toni et al.

The evolution of Generative Pre-trained Transformer (GPT) models has led to significant advancements in various natural language processing applications, particularly in legal textual entailment. We present an analysis of GPT-3.5 (ChatGPT) and GPT-4 performances on COLIEE Task 4 dataset, a prominent benchmark in this domain. The study encompasses data from Heisei 18 (2006) to Reiwa 3 (2021), exploring the models' abilities to discern entailment relationships within Japanese statute law across different periods. Our preliminary experimental results unveil intriguing insights into the models' strengths and weaknesses in handling legal textual entailment tasks, as well as the patterns observed in model performance. In the context of proprietary models with undisclosed architectures and weights, black-box analysis becomes crucial for evaluating their capabilities. We discuss the influence of training data distribution and the implications on the models' generalizability. This analysis serves as a foundation for future research, aiming to optimize GPT-based models and enable their successful adoption in legal information extraction and entailment applications.

Ha Thanh Nguyen, Wachara Fungwacharakorn, Sabine Wehnert et al.

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.

Wachara Fungwacharakorn, Kanae Tsushima, Hiroshi Hosobe et al.

Although various aspects of soft-constraint based norms have been explored, it is still challenging to understand preemption. Preemption is a situation where higher-level norms override lower-level norms when new information emerges. To address this, we propose a derivation state argumentation framework (DSA-framework). DSA-framework incorporates derivation states to explain how preemption arises based on evolving situational knowledge. Based on DSA-framework, we present an argumentative approach for explaining preemption. We formally prove that, under local optimality, DSA-framework can provide explanations why one consequence is obligatory or forbidden by soft-constraint based norms represented as logical constraint hierarchies.

Ha-Thanh Nguyen, Wachara Fungwacharakorn, Ken Satoh

Language serves as a vehicle for conveying thought, enabling communication among individuals. The ability to distinguish between diverse concepts, identify fairness and injustice, and comprehend a range of legal notions fundamentally relies on logical reasoning. Large Language Models (LLMs) attempt to emulate human language understanding and generation, but their competency in logical reasoning remains limited. This paper seeks to address the philosophical question: How can we effectively teach logical reasoning to LLMs while maintaining a deep understanding of the intricate relationship between language and logic? By focusing on bolstering LLMs' capabilities in logical reasoning, we aim to expand their applicability in law and other logic-intensive disciplines. To this end, we propose a Reinforcement Learning from Logical Feedback (RLLF) approach, which serves as a potential framework for refining LLMs' reasoning capacities. Through RLLF and a revised evaluation methodology, we explore new avenues for research in this domain and contribute to the development of LLMs capable of handling complex legal reasoning tasks while acknowledging the fundamental connection between language and logic.

Ha-Thanh Nguyen, Vu Tran, Ngoc-Cam Le et al.

Knowledge representation and reasoning in law are essential to facilitate the automation of legal analysis and decision-making tasks. In this paper, we propose a new approach based on legal science, specifically legal taxonomy, for representing and reasoning with legal documents. Our approach interprets the regulations in legal documents as binary trees, which facilitates legal reasoning systems to make decisions and resolve logical contradictions. The advantages of this approach are twofold. First, legal reasoning can be performed on the basis of the binary tree representation of the regulations. Second, the binary tree representation of the regulations is more understandable than the existing sentence-based representations. We provide an example of how our approach can be used to interpret the regulations in a legal document.

Nguyen Minh Phuong, Ha-Thanh Nguyen, May Myo Zin et al.

In this paper, we propose a pipeline leveraging Large Language Models (LLMs) for data augmentation in Information Extraction tasks within the legal domain. The proposed method is both simple and effective, significantly reducing the manual effort required for data annotation while enhancing the robustness of Information Extraction systems. Furthermore, the method is generalizable, making it applicable to various Natural Language Processing (NLP) tasks beyond the legal domain.

Ha-Thanh Nguyen, Ken Satoh

This paper introduces PYTHEN, a novel Python-based framework for defeasible legal reasoning. PYTHEN is designed to model the inherently defeasible nature of legal argumentation, providing a flexible and intuitive syntax for representing legal rules, conditions, and exceptions. Inspired by PROLEG (PROlog-based LEGal reasoning support system) and guided by the philosophy of The Zen of Python, PYTHEN leverages Python's built-in any() and all() functions to offer enhanced flexibility by natively supporting both conjunctive (ALL) and disjunctive (ANY) conditions within a single rule, as well as a more expressive exception-handling mechanism. This paper details the architecture of PYTHEN, provides a comparative analysis with PROLEG, and discusses its potential applications in autoformalization and the development of next-generation legal AI systems. By bridging the gap between symbolic reasoning and the accessibility of Python, PYTHEN aims to democratize formal legal reasoning for young researchers, legal tech developers, and professionals without extensive logic programming expertise. We position PYTHEN as a practical bridge between the powerful symbolic reasoning capabilities of logic programming and the rich, ubiquitous ecosystem of Python, making formal legal reasoning accessible to a broader range of developers and legal professionals.

Ha-Thanh Nguyen, Wachara Fungwacharakorn, Ken Satoh

Legal compliance in AI-driven data transfer planning is becoming increasingly critical under stringent privacy regulations such as the Japanese Act on the Protection of Personal Information (APPI). We propose a multi-agent legal verifier that decomposes compliance checking into specialized agents for statutory interpretation, business context evaluation, and risk assessment, coordinated through a structured synthesis protocol. Evaluated on a stratified dataset of 200 Amended APPI Article 16 cases with clearly defined ground truth labels and multiple performance metrics, the system achieves 72% accuracy, which is 21 percentage points higher than a single-agent baseline, including 90% accuracy on clear compliance cases (vs. 16% for the baseline) while maintaining perfect detection of clear violations. While challenges remain in ambiguous scenarios, these results show that domain specialization and coordinated reasoning can meaningfully improve legal AI performance, providing a scalable and regulation-aware framework for trustworthy and interpretable automated compliance verification.

Wachara Fungwacharakorn, Nguyen Ha Thanh, May Myo Zin et al.

This paper presents a novel approach termed Layer-of-Thoughts Prompting (LoT), which utilizes constraint hierarchies to filter and refine candidate responses to a given query. By integrating these constraints, our method enables a structured retrieval process that enhances explainability and automation. Existing methods have explored various prompting techniques but often present overly generalized frameworks without delving into the nuances of prompts in multi-turn interactions. Our work addresses this gap by focusing on the hierarchical relationships among prompts. We demonstrate that the efficacy of thought hierarchy plays a critical role in developing efficient and interpretable retrieval algorithms. Leveraging Large Language Models (LLMs), LoT significantly improves the accuracy and comprehensibility of information retrieval tasks.

Hai-Long Nguyen, Duc-Minh Nguyen, Tan-Minh Nguyen et al.

Large language models with billions of parameters, such as GPT-3.5, GPT-4, and LLaMA, are increasingly prevalent. Numerous studies have explored effective prompting techniques to harness the power of these LLMs for various research problems. Retrieval, specifically in the legal data domain, poses a challenging task for the direct application of Prompting techniques due to the large number and substantial length of legal articles. This research focuses on maximizing the potential of prompting by placing it as the final phase of the retrieval system, preceded by the support of two phases: BM25 Pre-ranking and BERT-based Re-ranking. Experiments on the COLIEE 2023 dataset demonstrate that integrating prompting techniques on LLMs into the retrieval system significantly improves retrieval accuracy. However, error analysis reveals several existing issues in the retrieval system that still need resolution.

Ha-Thanh Nguyen, Ken Satoh

Finetuning approaches in NLP often focus on exploitation rather than exploration, which may lead to suboptimal models. Given the vast search space of natural language, this limited exploration can restrict their performance in complex, high-stakes domains, where accurate negation understanding and logical reasoning abilities are crucial. To address this issue, we leverage Reinforcement Learning from Logical Feedback (RLLF) to create an effective balance between exploration and exploitation in LLMs. Our approach employs an appropriate benchmark dataset for training and evaluation, highlighting the importance of exploration in enhancing negation understanding capabilities. We compare the performance of our RLLF-enhanced LLMs with baseline models trained without RLLF, demonstrating the value of this balanced approach. Furthermore, we showcase the potential of our method in legal AI applications by employing transfer learning and evaluating its impact on negation understanding. Our experimental results exhibit the effectiveness of balancing exploration and exploitation with RLLF in improving LLMs' negation capabilities. This has implications for the development of more accurate, reliable, and logically consistent language models in high-stakes domains.

Juan Junqueras, Florian Boudin, May-Myo Zin et al.

Hate speech (HS) is a critical issue in online discourse, and one promising strategy to counter it is through the use of counter-narratives (CNs). Datasets linking HS with CNs are essential for advancing counterspeech research. However, even flagship resources like CONAN (Chung et al., 2019) annotate only a sparse subset of all possible HS-CN pairs, limiting evaluation. We introduce FC-CONAN (Fully Connected CONAN), the first dataset created by exhaustively considering all combinations of 45 English HS messages and 129 CNs. A two-stage annotation process involving nine annotators and four validators produces four partitions-Diamond, Gold, Silver, and Bronze-that balance reliability and scale. None of the labeled pairs overlap with CONAN, uncovering hundreds of previously unlabelled positives. FC-CONAN enables more faithful evaluation of counterspeech retrieval systems and facilitates detailed error analysis. The dataset is publicly available.

May-Myo Zin, Sabine Wehnert, Yuntao Kong et al.

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.

Zhihan Cao, Fumihito Nishino, Hiroaki Yamada et al.

We introduce JBE-QA, a Japanese Bar Exam Question-Answering dataset to evaluate large language models' legal knowledge. Derived from the multiple-choice (tanto-shiki) section of the Japanese bar exam (2015-2024), JBE-QA provides the first comprehensive benchmark for Japanese legal-domain evaluation of LLMs. It covers the Civil Code, the Penal Code, and the Constitution, extending beyond the Civil Code focus of prior Japanese resources. Each question is decomposed into independent true/false judgments with structured contextual fields. The dataset contains 3,464 items with balanced labels. We evaluate 26 LLMs, including proprietary, open-weight, Japanese-specialised, and reasoning models. Our results show that proprietary models with reasoning enabled perform best, and the Constitution questions are generally easier than the Civil Code or the Penal Code questions.

Ha-Thanh Nguyen, Ken Satoh, Francesca Toni et al.

Reasoning is an essential component of human intelligence in that it plays a fundamental role in our ability to think critically, support responsible decisions, and solve challenging problems. Traditionally, AI has addressed reasoning in the context of logic-based representations of knowledge. However, the recent leap forward in natural language processing, with the emergence of language models based on transformers, is hinting at the possibility that these models exhibit reasoning abilities, particularly as they grow in size and are trained on more and more data. Still, despite ongoing discussions about what reasoning is in language models, it is still not easy to articulate to what extent these models are actually capable of reasoning. The goal of this workshop is to create a platform for researchers from different disciplines and/or AI perspectives to explore approaches and techniques with the aim to reconcile reasoning between language models using transformers and logic-based representations. The specific objectives include analysing the reasoning abilities of language models measured alongside KR methods, injecting KR-style reasoning abilities into language models (including by neuro-symbolic means), and formalising the kind of reasoning language models carry out. This exploration aims to uncover how language models can effectively integrate and leverage knowledge and reasoning with it, thus improving their application and utility in areas where precision and reliability are key requirements.

Wachara Fungwacharakorn, Gauvain Bourgne, Ken Satoh

Precedential constraint is one foundation of case-based reasoning in AI and Law. It generally assumes that the underlying set of precedents must be consistent. To relax this assumption, a generalized notion of the reason model has been introduced. While several argumentative explanation approaches exist for reasoning with precedents based on the traditional consistent reason model, there has been no corresponding argumentative explanation method developed for this generalized reasoning framework accommodating inconsistent precedents. To address this question, this paper examines an extension of the derivation state argumentation framework (DSA-framework) to explain the reasoning according to the generalized notion of the reason model.

Thomas Ågotnes, Rustam Galimullin, Ken Satoh et al.

We formalise the notion of an anonymous public announcement in the tradition of public announcement logic. Such announcements can be seen as in-between a public announcement from ``the outside" (an announcement of $φ$) and a public announcement by one of the agents (an announcement of $K_aφ$): we get more information than just $φ$, but not (necessarily) about exactly who made it. Even if such an announcement is prima facie anonymous, depending on the background knowledge of the agents it might reveal the identity of the announcer: if I post something on a message board, the information might reveal who I am even if I don't sign my name. Furthermore, like in the Russian Cards puzzle, if we assume that the announcer's intention was to stay anonymous, that in fact might reveal more information. In this paper we first look at the case when no assumption about intentions are made, in which case the logic with an anonymous public announcement operator is reducible to epistemic logic. We then look at the case when we assume common knowledge of the intention to stay anonymous, which is both more complex and more interesting: in several ways it boils down to the notion of a ``safe" announcement (again, similarly to Russian Cards). Main results include formal expressivity results and axiomatic completeness for key logical languages.

Ha-Thanh Nguyen, Hiroaki Yamada, Ken Satoh

In this paper, we explore the application of Generative Pre-trained Transformers (GPTs) in cross-lingual legal Question-Answering (QA) systems using the COLIEE Task 4 dataset. In the COLIEE Task 4, given a statement and a set of related legal articles that serve as context, the objective is to determine whether the statement is legally valid, i.e., if it can be inferred from the provided contextual articles or not, which is also known as an entailment task. By benchmarking four different combinations of English and Japanese prompts and data, we provide valuable insights into GPTs' performance in multilingual legal QA scenarios, contributing to the development of more efficient and accurate cross-lingual QA solutions in the legal domain.

Ha-Thanh Nguyen, Minh-Phuong Nguyen, Thi-Hai-Yen Vuong et al.

In this paper, we introduce our approaches using Transformer-based models for different problems of the COLIEE 2021 automatic legal text processing competition. Automated processing of legal documents is a challenging task because of the characteristics of legal documents as well as the limitation of the amount of data. With our detailed experiments, we found that Transformer-based pretrained language models can perform well with automated legal text processing problems with appropriate approaches. We describe in detail the processing steps for each task such as problem formulation, data processing and augmentation, pretraining, finetuning. In addition, we introduce to the community two pretrained models that take advantage of parallel translations in legal domain, NFSP and NMSP. In which, NFSP achieves the state-of-the-art result in Task 5 of the competition. Although the paper focuses on technical reporting, the novelty of its approaches can also be an useful reference in automated legal document processing using Transformer-based models.

Ha-Thanh Nguyen, Phuong Minh Nguyen, Thi-Hai-Yen Vuong et al.

COLIEE is an annual competition in automatic computerized legal text processing. Automatic legal document processing is an ambitious goal, and the structure and semantics of the law are often far more complex than everyday language. In this article, we survey and report our methods and experimental results in using deep learning in legal document processing. The results show the difficulties as well as potentials in this family of approaches.

Ha-Thanh Nguyen, Vu Tran, Phuong Minh Nguyen et al.

Ambiguity is a characteristic of natural language, which makes expression ideas flexible. However, in a domain that requires accurate statements, it becomes a barrier. Specifically, a single word can have many meanings and multiple words can have the same meaning. When translating a text into a foreign language, the translator needs to determine the exact meaning of each element in the original sentence to produce the correct translation sentence. From that observation, in this paper, we propose ParaLaw Nets, a pretrained model family using sentence-level cross-lingual information to reduce ambiguity and increase the performance in legal text processing. This approach achieved the best result in the Question Answering task of COLIEE-2021.

Ha-Thanh Nguyen, Hai-Yen Thi Vuong, Phuong Minh Nguyen et al.

We propose deep learning based methods for automatic systems of legal retrieval and legal question-answering in COLIEE 2020. These systems are all characterized by being pre-trained on large amounts of data before being finetuned for the specified tasks. This approach helps to overcome the data scarcity and achieve good performance, thus can be useful for tackling related problems in information retrieval, and decision support in the legal domain. Besides, the approach can be explored to deal with other domain specific problems.

Vu Tran, Minh Le Nguyen, Ken Satoh

We present our method for tackling the legal case retrieval task of the Competition on Legal Information Extraction/Entailment 2019. Our approach is based on the idea that summarization is important for retrieval. On one hand, we adopt a summarization based model called encoded summarization which encodes a given document into continuous vector space which embeds the summary properties of the document. We utilize the resource of COLIEE 2018 on which we train the document representation model. On the other hand, we extract lexical features on different parts of a given query and its candidates. We observe that by comparing different parts of the query and its candidates, we can achieve better performance. Furthermore, the combination of the lexical features with latent features by the summarization-based method achieves even better performance. We have achieved the state-of-the-art result for the task on the benchmark of the competition.

Vu Tran, Minh Le Nguyen, Ken Satoh

In this paper, we present a method of automatic catchphrase extracting from legal case documents. We utilize deep neural networks for constructing scoring model of our extraction system. We achieve comparable performance with systems using corpus-wide and citation information which we do not use in our system.

Lai Dac Viet, Vu Trong Sinh, Nguyen Le Minh et al.

Convolutional neural networks (CNN) have recently achieved remarkable performance in a wide range of applications. In this research, we equip convolutional sequence-to-sequence (seq2seq) model with an efficient graph linearization technique for abstract meaning representation parsing. Our linearization method is better than the prior method at signaling the turn of graph traveling. Additionally, convolutional seq2seq model is more appropriate and considerably faster than the recurrent neural network models in this task. Our method outperforms previous methods by a large margin on both the standard dataset LDC2014T12. Our result indicates that future works still have a room for improving parsing model using graph linearization approach.

Ryuta Arisaka, Ken Satoh

The act of persuasion, a key component in rhetoric argumentation, may be viewed as a dynamics modifier. We extend Dung's frameworks with acts of persuasion among agents, and consider interactions among attack, persuasion and defence that have been largely unheeded so far. We characterise basic notions of admissibilities in this framework, and show a way of enriching them through, effectively, CTL (computation tree logic) encoding, which also permits importation of the theoretical results known to the logic into our argumentation frameworks. Our aim is to complement the growing interest in coordination of static and dynamic argumentation.

Ryuta Arisaka, Ken Satoh

We consider abstract-argumentation-theoretic coalition formability in this work. Taking a model from political alliance among political parties, we will contemplate profitability, and then formability, of a coalition. As is commonly understood, a group forms a coalition with another group for a greater good, the goodness measured against some criteria. As is also commonly understood, however, a coalition may deliver benefits to a group X at the sacrifice of something that X was able to do before coalition formation, which X may be no longer able to do under the coalition. Use of the typical conflict-free sets of arguments is not very fitting for accommodating this aspect of coalition, which prompts us to turn to a weaker notion, conflict-eliminability, as a property that a set of arguments should primarily satisfy. We require numerical quantification of attack strengths as well as of argument strengths for its characterisation. We will first analyse semantics of profitability of a given conflict-eliminable set forming a coalition with another conflict-eliminable set, and will then provide four coalition formability semantics, each of which formalises certain utility postulate(s) taking the coalition profitability into account.

Megumi Fujita, Yuki Goto, Naoyuki Nide et al.

In the real world, robots with embodiment face various issues such as dynamic continuous changes of the environment and input/output disturbances. The key to solving these issues can be found in daily life; people `do actions associated with sensing' and `dynamically change their plans when necessary'. We propose the use of a new concept, enabling robots to do these two things, for autonomously controlling mobile robots. We implemented our concept to make two experiments under static/dynamic environments. The results of these experiments show that our idea provides a way to adapt to dynamic changes of the environment in the real world.