Evaluating long-form answers in high-stakes domains such as law or medicine remains a fundamental challenge. Standard metrics like BLEU and ROUGE fail to capture semantic correctness, and current LLM-based evaluators often reduce nuanced aspects of answer quality into a single undifferentiated score. We introduce DeCE, a decomposed LLM evaluation framework that separates precision (factual accuracy and relevance) and recall (coverage of required concepts), using instance-specific criteria automatically extracted from gold answer requirements. DeCE is model-agnostic and domain-general, requiring no predefined taxonomies or handcrafted rubrics. We instantiate DeCE to evaluate different LLMs on a real-world legal QA task involving multi-jurisdictional reasoning and citation grounding. DeCE achieves substantially stronger correlation with expert judgments (r=0.78), compared to traditional metrics (r=0.12) and pointwise LLM scoring (r=0.35). It also reveals interpretable trade-offs: generalist models favor recall, while specialized models favor precision. Importantly, only 11.95% of LLM-generated criteria required expert revision, underscoring DeCE’s scalability. DeCE offers an interpretable and actionable LLM evaluation framework in expert domains.

The use of large language models (LLMs) for zero- or few-shot prompting in natural language processing has given rise to a new research area known as prompt engineering. Recent studies have demonstrated that Chain-of-Thought (CoT) prompts can lead to significant improvements in tasks such as arithmetic and common-sense reasoning. This paper explores the use of such approaches in legal reasoning tasks by conducting experiments on the COLIEE entailment task, which is based on the Japanese Bar exam. We evaluate zero-shot/few-shot and fine-tuning approaches with and without explanations, as well as various prompting strategies. Our results indicate that while CoT prompting and fine-tuning with explanations can improve performance, the best results are achieved with prompts derived from specific legal reasoning techniques, such as IRAC (Issue, Rule, Application, Conclusion). In addition, we observe that few-shot learning where the demonstrations are derived from clustering past training data consistently yields high performance on the COLIEE entailment task for both the years of the data that we tested. Through our experiments, we improve the previous best result on the 2021 COLIEE task from 0.7037 to 0.8025 and surpass the best system from 2022 with an accuracy of 0.789.

Legal litigation planning can benefit from statistics collected from past decisions made by judges. Information on the typical duration for a submitted motion, for example, can give valuable clues for developing a successful strategy. Such information is encoded in semi-structured documents called dockets. In order to extract and aggregate this information, we deployed various information extraction and machine learning techniques. The aggregated data can be queried in real time within the Westlaw Edge search engine. In addition to a keyword search for judges, lawyers, law firms, parties and courts, we also implemented a question answering interface that offers targeted questions in order to get to the respective answers quicker.

Dockets contain a wealth of information for planning a litigation strategy, but the information is locked up in semi-structured text. Manually deriving the outcomes for each party (e.g., settlement, verdict) would be very labor intensive. Having such information available for every past court case, however, would be very useful for developing a strategy because it potentially reveals tendencies and trends of judges and courts and the opposing counsel. We used Natural Language Processing (NLP) techniques and deep learning methods allowing us to scale the automatic analysis of millions of US federal court dockets. The automatically extracted information is fed into a Litigation Analytics tool that is used by lawyers to plan how they approach concrete litigations.

This paper presents the two systems we entered into the 2017 E2E NLG Challenge: TemplGen, a templated-based system and SeqGen, a neural network-based system. Through the automatic evaluation, SeqGen achieved competitive results compared to the template-based approach and to other participating systems as well. In addition to the automatic evaluation, in this paper we present and discuss the human evaluation results of our two systems.

We discuss the ethical implications of Natural Language Generation systems. We use one particular system as a case study to identify and classify issues, and we provide an ethics checklist, in the hope that future system designers may benefit from conducting their own ethics reviews based on our checklist.

This talk will present a few NLG systems developed within Thomson Reuters providing information to professionals such as lawyers, accountants or traders. Based on the experience developing these system, I will discuss the usefulness of automatic metrics, crowd-sourced evaluation, corpora studies and expert reviews. I will conclude with exploring the question of whether developers of NLG systems need to follow ethical guidelines and how those guidelines could be established.