Learning from Litigation: Graphs and LLMs for Retrieval and Reasoning in eDiscovery

• URL: http://arxiv.org/abs/2405.19164v2
• Date: Fri, 13 Jun 2025 14:26:31 GMT
• Title: Learning from Litigation: Graphs and LLMs for Retrieval and Reasoning in eDiscovery
• Authors: Sounak Lahiri, Sumit Pai, Tim Weninger, Sanmitra Bhattacharya,
• Abstract summary: We introduce DISCOvery Graph (DISCOG), an emerging system that integrates knowledge graphs for enhanced document ranking and classification.<n> DISCOG outperforms strong baselines in F1-score, precision, and recall across both balanced and imbalanced datasets.<n>In real-world deployments, it has reduced litigation-related document review costs by approximately 98%, demonstrating significant business impact.
• Score: 6.037276428689637
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Electronic Discovery (eDiscovery) requires identifying relevant documents from vast collections for legal production requests. While artificial intelligence (AI) and natural language processing (NLP) have improved document review efficiency, current methods still struggle with legal entities, citations, and complex legal artifacts. To address these challenges, we introduce DISCOvery Graph (DISCOG), an emerging system that integrates knowledge graphs for enhanced document ranking and classification, augmented by LLM-driven reasoning. DISCOG outperforms strong baselines in F1-score, precision, and recall across both balanced and imbalanced datasets. In real-world deployments, it has reduced litigation-related document review costs by approximately 98\%, demonstrating significant business impact.

Related papers

• Verifying the Verifiers: Unveiling Pitfalls and Potentials in Fact Verifiers [59.168391398830515]
  We evaluate 12 pre-trained LLMs and one specialized fact-verifier, using a collection of examples from 14 fact-checking benchmarks.<n>We highlight the importance of addressing annotation errors and ambiguity in datasets.<n> frontier LLMs with few-shot in-context examples, often overlooked in previous works, achieve top-tier performance.
  arXiv  Detail & Related papers  (2025-06-16T10:32:10Z)
• Does Machine Unlearning Truly Remove Model Knowledge? A Framework for Auditing Unlearning in LLMs [58.24692529185971]
  We introduce a comprehensive auditing framework for unlearning evaluation comprising three benchmark datasets, six unlearning algorithms, and five prompt-based auditing methods.<n>We evaluate the effectiveness and robustness of different unlearning strategies.
  arXiv  Detail & Related papers  (2025-05-29T09:19:07Z)
• Document Attribution: Examining Citation Relationships using Large Language Models [62.46146670035751]
  We propose a zero-shot approach that frames attribution as a straightforward textual entailment task.<n>We also explore the role of the attention mechanism in enhancing the attribution process.
  arXiv  Detail & Related papers  (2025-05-09T04:40:11Z)
• Improving the Accuracy and Efficiency of Legal Document Tagging with Large Language Models and Instruction Prompts [0.6554326244334866]
  Legal-LLM is a novel approach that leverages the instruction-following capabilities of Large Language Models (LLMs) through fine-tuning.<n>We evaluate our method on two benchmark datasets, POSTURE50K and EURLEX57K, using micro-F1 and macro-F1 scores.
  arXiv  Detail & Related papers  (2025-04-12T18:57:04Z)
• Integrated ensemble of BERT- and features-based models for authorship attribution in Japanese literary works [2.624902795082451]
  Authorship attribution (AA) tasks rely on statistical data analysis and classification based on stylistic features extracted from texts. In this study, we aimed to significantly improve performance using an integrated integrative ensemble of traditional feature-based and modern PLM-based methods on an AA task in a small sample.
  arXiv  Detail & Related papers  (2025-04-11T13:40:50Z)
• Lightweight and Direct Document Relevance Optimization for Generative Information Retrieval [49.669503570350166]
  Generative information retrieval (GenIR) is a promising neural retrieval paradigm that formulates document retrieval as a document identifier (docid) generation task. Existing GenIR models suffer from token-level misalignment, where models trained to predict the next token often fail to capture document-level relevance effectively. We propose direct document relevance optimization (DDRO), which aligns token-level docid generation with document-level relevance estimation through direct optimization via pairwise ranking.
  arXiv  Detail & Related papers  (2025-04-07T15:27:37Z)
• Aplicação de Large Language Models na Análise e Síntese de Documentos Jurídicos: Uma Revisão de Literatura [0.0]
  Large Language Models (LLMs) have been increasingly used to optimize the analysis and synthesis of legal documents.<n>This study aims to conduct a systematic literature review to identify the state of the art in prompt engineering applied to LLMs in the legal context.
  arXiv  Detail & Related papers  (2025-04-01T12:34:00Z)
• Named entity recognition for Serbian legal documents: Design, methodology and dataset development [0.0]
  We present one solution for Named Entity Recognition (NER) in the case of legal documents written in Serbian language.<n>It leverages on the pre-trained bidirectional encoder representations from transformers (BERT), which had been carefully adapted to the specific task of identifying and classifying specific data points from textual content.
  arXiv  Detail & Related papers  (2025-02-14T22:23:39Z)
• Optimizing Pretraining Data Mixtures with LLM-Estimated Utility [52.08428597962423]
  Large Language Models improve with increasing amounts of high-quality training data. We find token-counts outperform manual and learned mixes, indicating that simple approaches for dataset size and diversity are surprisingly effective. We propose two complementary approaches: UtiliMax, which extends token-based $200s by incorporating utility estimates from reduced-scale ablations, achieving up to a 10.6x speedup over manual baselines; and Model Estimated Data Utility (MEDU), which leverages LLMs to estimate data utility from small samples, matching ablation-based performance while reducing computational requirements by $simx.
  arXiv  Detail & Related papers  (2025-01-20T21:10:22Z)
• JudgeRank: Leveraging Large Language Models for Reasoning-Intensive Reranking [81.88787401178378]
  We introduce JudgeRank, a novel agentic reranker that emulates human cognitive processes when assessing document relevance. We evaluate JudgeRank on the reasoning-intensive BRIGHT benchmark, demonstrating substantial performance improvements over first-stage retrieval methods. In addition, JudgeRank performs on par with fine-tuned state-of-the-art rerankers on the popular BEIR benchmark, validating its zero-shot generalization capability.
  arXiv  Detail & Related papers  (2024-10-31T18:43:12Z)
• Context is Key: A Benchmark for Forecasting with Essential Textual Information [87.3175915185287]
  "Context is Key" (CiK) is a time series forecasting benchmark that pairs numerical data with diverse types of carefully crafted textual context. We evaluate a range of approaches, including statistical models, time series foundation models, and LLM-based forecasters. Our experiments highlight the importance of incorporating contextual information, demonstrate surprising performance when using LLM-based forecasting models, and also reveal some of their critical shortcomings.
  arXiv  Detail & Related papers  (2024-10-24T17:56:08Z)
• Scalable Influence and Fact Tracing for Large Language Model Pretraining [14.598556308631018]
  Training data attribution (TDA) methods aim to attribute model outputs back to specific training examples. We refine existing gradient-based methods to work effectively at scale. We release our prompt set and model outputs, along with a web-based visualization tool to explore influential examples.
  arXiv  Detail & Related papers  (2024-10-22T20:39:21Z)
• Evaluating Human Alignment and Model Faithfulness of LLM Rationale [66.75309523854476]
  We study how well large language models (LLMs) explain their generations through rationales. We show that prompting-based methods are less "faithful" than attribution-based explanations.
  arXiv  Detail & Related papers  (2024-06-28T20:06:30Z)
• Enhancing Text Classification through LLM-Driven Active Learning and Human Annotation [2.0411082897313984]
  This study introduces a novel methodology that integrates human annotators and Large Language Models. The proposed framework integrates human annotation with the output of LLMs, depending on the model uncertainty levels. The empirical results show a substantial decrease in the costs associated with data annotation while either maintaining or improving model accuracy.
  arXiv  Detail & Related papers  (2024-06-17T21:45:48Z)
• Prompt-based vs. Fine-tuned LLMs Toward Causal Graph Verification [0.0]
  This work aims toward an application of natural language processing (NLP) technology for automatic verification of causal graphs using text sources. We compare the performance of two types of NLP models: (1) pre-trained language models fine-tuned for causal relation classification task and, (2) prompt-based LLMs.
  arXiv  Detail & Related papers  (2024-05-29T09:06:18Z)
• Empowering Prior to Court Legal Analysis: A Transparent and Accessible Dataset for Defensive Statement Classification and Interpretation [5.646219481667151]
  This paper introduces a novel dataset tailored for classification of statements made during police interviews, prior to court proceedings. We introduce a fine-tuned DistilBERT model that achieves state-of-the-art performance in distinguishing truthful from deceptive statements. We also present an XAI interface that empowers both legal professionals and non-specialists to interact with and benefit from our system.
  arXiv  Detail & Related papers  (2024-05-17T11:22:27Z)
• Evaluating Generative Language Models in Information Extraction as Subjective Question Correction [49.729908337372436]
  We propose a new evaluation method, SQC-Score. Inspired by the principles in subjective question correction, we propose a new evaluation method, SQC-Score. Results on three information extraction tasks show that SQC-Score is more preferred by human annotators than the baseline metrics.
  arXiv  Detail & Related papers  (2024-04-04T15:36:53Z)
• Harnessing the Power of Large Language Model for Uncertainty Aware Graph Processing [24.685942503019948]
  We introduce a novel approach that harnesses the power of a large language model (LLM) to provide a confidence score on the generated answer. We experiment with our approach on two graph processing tasks: few-shot knowledge graph completion and graph classification. Our confidence measure achieves an AUC of 0.8 or higher on seven out of the ten datasets in predicting the correctness of the answer generated by LLM.
  arXiv  Detail & Related papers  (2024-03-31T07:38:39Z)
• Adapting LLMs for Efficient, Personalized Information Retrieval: Methods and Implications [0.7832189413179361]
  Large Language Models (LLMs) excel in comprehending and generating human-like text. This paper explores strategies for integrating Language Models (LLMs) with Information Retrieval (IR) systems.
  arXiv  Detail & Related papers  (2023-11-21T02:01:01Z)
• Bias and Fairness in Large Language Models: A Survey [73.87651986156006]
  We present a comprehensive survey of bias evaluation and mitigation techniques for large language models (LLMs) We first consolidate, formalize, and expand notions of social bias and fairness in natural language processing. We then unify the literature by proposing three intuitive, two for bias evaluation, and one for mitigation.
  arXiv  Detail & Related papers  (2023-09-02T00:32:55Z)
• GERE: Generative Evidence Retrieval for Fact Verification [57.78768817972026]
  We propose GERE, the first system that retrieves evidences in a generative fashion. The experimental results on the FEVER dataset show that GERE achieves significant improvements over the state-of-the-art baselines.
  arXiv  Detail & Related papers  (2022-04-12T03:49:35Z)
• SAIS: Supervising and Augmenting Intermediate Steps for Document-Level Relation Extraction [51.27558374091491]
  We propose to explicitly teach the model to capture relevant contexts and entity types by supervising and augmenting intermediate steps (SAIS) for relation extraction. Based on a broad spectrum of carefully designed tasks, our proposed SAIS method not only extracts relations of better quality due to more effective supervision, but also retrieves the corresponding supporting evidence more accurately.
  arXiv  Detail & Related papers  (2021-09-24T17:37:35Z)
• Integrating Semantics and Neighborhood Information with Graph-Driven Generative Models for Document Retrieval [51.823187647843945]
  In this paper, we encode the neighborhood information with a graph-induced Gaussian distribution, and propose to integrate the two types of information with a graph-driven generative model. Under the approximation, we prove that the training objective can be decomposed into terms involving only singleton or pairwise documents, enabling the model to be trained as efficiently as uncorrelated ones.
  arXiv  Detail & Related papers  (2021-05-27T11:29:03Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.