Aspassia Daskalopulu, Marek Sergot
The paper outlines ongoing research on logic-based tools for the analysis and representation of legal contracts of the kind frequently encountered in large-scale engineering projects and complex, long-term trading agreements. We consider both contract formation and contract performance, in each case identifying the representational issues and the prospects for providing automated support tools.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
继续探索
Towards Robust Legal Reasoning: Harnessing Logical LLMs in Law
针对法律文本处理中LLM准确性与透明度不足的问题，提出神经符号方法结合逻辑推理，在保险合同承保查询中验证了引导式LLM+逻辑框架的有效性。
Legal Compliance Evaluation of Smart Contracts Generated By Large Language Models
本文研究大语言模型生成合法合规智能合约的能力，提出一套通过将法律合约与智能合约建模为流程并比较行为来量化法律合规性的度量标准，实验表明大模型合规性更高且该度量标准为自动化开发奠定基础。
ContractEval: Benchmarking LLMs for Clause-Level Legal Risk Identification in Commercial Contracts
ContractEval基准评估开源与专有LLMs在商业合同条款级法律风险识别上的表现，发现专有模型更优，开源模型需针对性微调以提升正确性与有效性。
Fine-tuning language models, such as BERT, on domain specific corpora has proven to be valuable in domains like scientific papers and biomedical text. In this paper, we show that fine-tuning BERT on legal documents similarly provides valuable improvements on NLP tasks in the legal domain. Demonstrating this outcome is significant for analyzing commercial agreements, because obtaining large legal corpora is challenging due to their confidential nature. As such, we show that having access to large legal corpora is a competitive advantage for commercial applications, and academic research on anal…
In contract analysis and contract automation, a knowledge base (KB) of legal entities is fundamental for performing tasks such as contract verification, contract generation and contract analytic. However, such a KB does not always exist nor can be produced in a short time. In this paper, we propose a clustering-based approach to automatically generate a reliable knowledge base of legal entities from given contracts without any supplemental references. The proposed method is robust to different types of errors brought by pre-processing such as Optical Character Recognition (OCR) and Named Entit…
This paper concentrates on the representation of the legal relations that obtain between parties once they have entered a contractual agreement and their evolution as the agreement progresses through time. Contracts are regarded as process and they are analysed in terms of the obligations that are active at various points during their life span. An informal notation is introduced that summarizes conveniently the states of an agreement as it evolves over time. Such a representation enables us to determine what the status of an agreement is, given an event or a sequence of events that concern th…
LegalPro-BERT: Classification of Legal Provisions by fine-tuning BERT Large Language Model
针对合同法律条款分类中专业词汇与标注数据不足的问题，本文提出并微调基于 BERT 的 LegalPro-BERT，实验表明其优于现有基准。
A Survey of Classification Tasks and Approaches for Legal Contracts
该综述聚焦法律合同分类（LCC）领域，梳理7项分类任务、14个英文合同数据集及三类方法体系，讨论评估技术与最优结果，提出未来研究方向，为法律NLP研究者和从业者提供参考。
Towards Mitigating Perceived Unfairness in Contracts from a Non-Legal Stakeholder's Perspective
本文从非法律利益相关者视角研究合同条款的感知不公平问题，通过实证分析不同利益相关者观点，并比较思维链提示与半监督微调方法，证明基于BERT的微调在识别不公平条款上准确率达84%，优于Vicuna-13B思维链提示9个百分点。
LAW: Legal Agentic Workflows for Custody and Fund Services Contracts
针对托管与基金服务合同处理难题，提出模块化法律智能体工作流LAW，集成专用工具与智能体，显著提升复杂任务性能，较基线高92.9个百分点，且成本更低。
ContractScrub: A benchmark for final review of legal contracts
针对合同 scrubbing 任务，研究人员推出首个基准测试 ContractScrub，发现前沿 LLMs 在该任务上表现不佳，凸显了领域特定基准的重要性。
LLMs in Interpreting Legal Documents
本文研究了大型语言模型在法律文件解释中的应用，探讨了其在优化法律任务中的潜力及面临的挑战。
Clause recommendation is the problem of recommending a clause to a legal contract, given the context of the contract in question and the clause type to which the clause should belong. With not much prior work being done toward the generation of legal contracts, this problem was proposed as a first step toward the bigger problem of contract generation. As an open-ended text generation problem, the distinguishing characteristics of this problem lie in the nature of legal language as a sublanguage and the considerable similarity of textual content within the clauses of a specific type. This simil…
The paper develops a logical understanding of processes for signature of legal contracts, motivated by applications to legal recognition of smart contracts on blockchain platforms. A number of axioms and rules of inference are developed that can be used to justify a ``meeting of the minds'' precondition for contract formation from the fact that certain content has been signed. In addition to an ``offer and acceptance'' process, the paper considers ``signature in counterparts'', a legal process that permits a contract between two or more parties to be brought into force by having the parties in…
Metadata Extraction Leveraging Large Language Models
本研究针对合同审查中的法律元数据提取需求，结合公开与专有数据集，通过优化文本转换、块选择及CoT提示、结构化工具调用等LLM技术，显著提升了条款识别的准确率与效率，可为法律从业者提供低成本高效的合同审查工具。
Equitable Access to Justice: Logical LLMs Show Promise
本文探讨将LLMs与逻辑编程结合以增强法律推理能力，证明OpenAI o1-preview能成功编码保险合同为逻辑程序，从而提升司法可及性。
Bridging Legal Interpretation and Formal Logic: Faithfulness, Assumption, and the Future of AI Legal Reasoning
本文提出一种结合大语言模型与形式验证的神经符号方法，旨在提升AI辅助法律推理的可靠性与可信度，减少人工验证负担。
We propose a new formalization of legal competences, and in particular for the Hohfeldian categories of power and immunity, through a deontic reinterpretation of dynamic epistemic logic. We argue that this logic explicitly captures the norm-changing character of legal competences while providing a sophisticated reduction of the latter to static normative positions. The logic is completely axiomatizable, and we apply it to a concrete case in German contract law to illustrate that it can capture the distinction between legal ability and legal permissibility.
Contractual Deepfakes: Can Large Language Models Generate Contracts?
本文指出大语言模型生成的合同可能不具法律效力，质疑其在法律领域应用的可行性。
This paper aims to investigate the possibility of using artificial intelligence (AI) to resolve the legal issues raised by the Covid-19 emergency about the fate of continuing execution contracts, or those with deferred or periodic execution, as well as, more generally, to deal with exceptional events and contingencies. We first study whether the Italian legal system allows for ''maintenance'' remedies to cope with contingencies and to avoid the termination of the contract, while ensuring effective protection of the interests of both parties. We then give a complete and technical description of…
A Comprehensive Framework for Reliable Legal AI: Combining Specialized Expert Systems and Adaptive Refinement
本文提出结合混合专家系统、知识架构及RAG、KG、RLHF等技术的法律AI框架，有效缓解模型幻觉问题，显著提升法律任务准确性与可靠性。
Artificial Intelligence (AI) is taking on increasingly autonomous roles, e.g., browsing the web as a research assistant and managing money. But specifying goals and restrictions for AI behavior is difficult. Similar to how parties to a legal contract cannot foresee every potential "if-then" contingency of their future relationship, we cannot specify desired AI behavior for all circumstances. Legal standards facilitate robust communication of inherently vague and underspecified goals. Instructions (in the case of language models, "prompts") that employ legal standards will allow AI agents to de…
Despite the 'apparent clarity' of a given legal provision, its application may result in an outcome that does not exactly conform to the semantic level of a statute. The vagueness within a legal text is induced intentionally to accommodate all possible scenarios under which such norms should be applied, thus making the role of pragmatics an important aspect also in the representation of a legal norm and reasoning on top of it. The notion of pragmatics considered in this paper does not focus on the aspects associated with judicial decision making. The paper aims to shed light on the aspects of …
The use of Structured English as a computation independent knowledge representation format for non-technical users in business rules representation has been proposed in OMGs Semantics and Business Vocabulary Representation (SBVR). In the legal domain we face a similar problem. Formal representation languages, such as OASIS LegalRuleML and legal ontologies (LKIF, legal OWL2 ontologies etc.) support the technical knowledge engineer and the automated reasoning. But, they can be hardly used directly by the legal domain experts who do not have a computer science background. In this paper we adapt t…
A prototype for automated reasoning over legal texts, called NAI, is presented. As an input, NAI accepts formalized logical representations of such legal texts that can be created and curated using an integrated annotation interface. The prototype supports automated reasoning over the given text representation and multiple quality assurance procedures. The pragmatics of the NAI suite as well its feasibility in practical applications is studied on a fragment of the Smoking Prohibition (Children in Motor Vehicles) (Scotland) Act 2016 of the Scottish Parliament.
Agent TCP/IP: An Agent-to-Agent Transaction System
针对现有智能体框架缺乏交互标准协议、智能体相互隔绝的问题，提出ATCP/IP协议，通过链上可编程合约与法律封装层实现智能体间知识产权交易，构建无需人工中介的新兴知识经济。
PRecG: Legal Precedent Retrieval with Graph Neural Networks and Rhetorical Role Segmentation
研究法律先例检索问题，提出PRecG管道，通过基于句子修辞角色分解文档、构建知识图、学习聚合实体上下文表示等步骤，分层学习法律判决对的表示来计算相似度，经实验验证其有效性。
From Legal Text to Executable Decision Models: Evaluating Structured Representations for Legal Decision Model Generation
本文研究通过结构化表示提升基于LLM的法律决策模型生成效果，发现输入约束显著提升模型相似度，且结构相似性与结果等价性互补。
On Verifiable Legal Reasoning: A Multi-Agent Framework with Formalized Knowledge Representations
本文提出一种模块化多智能体框架，通过形式化知识表示将法律推理分解为知识获取与应用阶段，结合符号推理提升可验证性和透明度，在税款计算任务上显著提升准确率。
We present an approach for modelling the structure and coarse content of legal documents with a view to providing automated support for the drafting of contracts and contract database retrieval. The approach is designed to be applicable where contract drafting is based on model-form contracts or on existing examples of a similar type. The main features of the approach are: (1) the representation addresses the structure and the interrelationships between the constituent parts of contracts, but not the text of the document itself; (2) the representation of documents is separated from the mechani…
Annotating Topical Legal Insights from Case Proceedings
本文提出法律数据注释系统LeDA，可动态创建注释标签，用于注释印度最高法院案例诉讼中的法律概念，构建文档语义表示以支持先例检索等下游任务。
Using LLMs to Discover Legal Factors
本文提出一种利用大型语言模型从原始法院意见中发现法律因素及相关定义的半自动化方法，实验证明该方法生成的因素表示能以中等成功率预测案件结果。
A key challenge in the legal domain is the adaptation and representation of the legal knowledge expressed through texts, in order for legal practitioners and researchers to access this information easier and faster to help with compliance related issues. One way to approach this goal is in the form of a taxonomy of legal concepts. While this task usually requires a manual construction of terms and their relations by domain experts, this paper describes a methodology to automatically generate a taxonomy of legal noun concepts. We apply and compare two approaches on a corpus consisting of statut…
Commitment To Cooperation With Self-Negotiated Contracts
研究人工智能代理在多智能体世界中的合作问题，借鉴法律制度和契约，通过在时空博弈\CT中研究基于大型语言模型的代理使用不同合同表示，发现自我协商合同可改善合作结果。
Automatic charge prediction task aims to determine the final charges based on fact descriptions of criminal cases, which is a vital application of legal assistant systems. Conventional works usually depend on fact descriptions to predict charges while ignoring the legal schematic knowledge, which makes it difficult to distinguish confusing charges. In this paper, we propose a knowledge-attentive neural network model, which introduces legal schematic knowledge about charges and exploit the knowledge hierarchical representation as the discriminative features to differentiate confusing charges. O…
Contracts are a common type of legal document that frequent in several day-to-day business workflows. However, there has been very limited NLP research in processing such documents, and even lesser in generating them. These contracts are made up of clauses, and the unique nature of these clauses calls for specific methods to understand and generate such documents. In this paper, we introduce the task of clause recommendation, asa first step to aid and accelerate the author-ing of contract documents. We propose a two-staged pipeline to first predict if a specific clause type is relevant to be a…
Several solutions for specifying normative artefacts (norms, contracts, policies) in a computational processable way have been presented in the literature. Legal core ontologies have been proposed to systematize concepts and relationships relevant to normative reasoning. However, no solution amongst those has achieved general acceptance, and no common ground (representational, computational) has been identified enabling us to easily compare them. Yet, all these efforts share the same motivation of representing normative directives, therefore it is plausible that there may be a representational…
扫码添加微信好友，提出您的宝贵建议 👇
💡 备注请填写：网站反馈
发表机构由 AI 从论文文本抽取，如发现错误，欢迎反馈修正建议。