India

Legal document analysis is pivotal in modern judicial systems, particularly for case retrieval, classification, and recommendation tasks. Graph neural networks (GNNs) have revolutionized legal use cases by enabling the efficient analysis of complex relationships. Although existing legal citation network datasets have significantly advanced research in this domain, the lack of large-scale open-source datasets tailored to the Indian judicial system has limited progress. To address this gap, we present the Indian Legal Citation Network (LeCNet) - the first open-source benchmark dataset for the link prediction task (missing citation recommendation) in the Indian judicial context. The dataset has been created by extracting information from the original judgments. LeCNet comprises 26,308 nodes representing case judgments and 67,108 edges representing citation relationships between the case nodes. Each node is described with rich features of document embeddings that incorporate contextual information from the case documents. Baseline experiments using various machine learning models were conducted for dataset validation. The Mean Reciprocal Rank (MRR) metric is used for model evaluation. The results obtained demonstrate the utility of the LeCNet dataset, highlighting the advantages of graph-based representations over purely textual models.

IJCNLP-AACL 2025

LeCNet: A Legal Citation Network Benchmark Dataset

legal citation network

indian legal ai

link predicition

graph neural networks

**Welcome to EMNLP 2023!**

On behalf of the EMNLP 2023 Organizing Committee, I extend a warm and heartfelt welcome to all of you to the 2023 Conference on Empirical Methods in Natural Language Processing (EMNLP). It is with immense pleasure and excitement that we gather here in Singapore, a vibrant hub of innovation and technological advancement.

The conference program is packed with insightful presentations, thought-provoking workshops, and engaging networking opportunities. In addition to the technical sessions, we have also planned several social events that will provide you with the opportunity to connect with your colleagues.

The conference is held in person at the Resorts World Convention Centre in Singapore, and available on-line with the help of Underline.

For those in Singapore, I hope that you will find time to explore the exciting Sentosa Island, Gardens by the Bay, Singapore Botanic Gardens and the many other attractions unique to Singapore.

Of course, we are grateful to our sponsors and partners for their generous support of EMNLP 2023, whose contributions make it possible for us to host this world-class event.

Yuji Matsumoto (RIKEN AIP) 
EMNLP 2023 General Chair

To access the **EMNLP 2023** event page on Underline, you need to register for the Conference. 
Please follow **[this link](https://2023.emnlp.org/registration/)** for more details.

EMNLP 2023

EMNLP 2023 took place in Singapore from Dec 6th to Dec 10th, 2023.

workshop paper

### Welcome to IJCNLP-AACL 2025! 
 It is a great honor to host this joint conference in Mumbai, India, from December 20 to 24, 2025. The joint conferences of IJCNLP and AACL are organized with alternating leadership in the Asia-Pacific region. The event is run by the Asian Federation of Natural Language Processing (AFNLP) in odd years, and by AACL in even years, while it is organized solely by ACL when the annual ACL meeting is held in the region. This year, the conference is primarily organized by AFNLP. 
*Kentaro Inui
MBZUAI, UAE
General Chair, IJCNLP-AACL 2025* 
Read full message and download the Conference Handbook [**here**](https://drive.google.com/file/d/1UTwxkAqSqI-GAoJC3wE1zZt5VP1Y8GX0/view?usp=sharing).

The 14th IJCNLP & 4th AACL will be held in Mumbai, India from December 20th to December 24th, 2025.

As large language models (LLMs) become increasingly embedded in our daily lives, evaluating their quality and reliability across diverse contexts has become essential. While comprehensive benchmarks exist for assessing LLM performance in English, there remains a significant gap in evaluation resources for other languages. Moreover, because most LLMs are trained primarily on data rooted in European and American cultures, they often lack familiarity with non-Western cultural contexts. To address this limitation, our study focuses on the Persian language and Iranian culture. We introduce 19 new evaluation datasets specifically designed to assess LLMs on topics such as Iranian law, Persian grammar, Persian idioms, and university entrance exams. Using these datasets, we benchmarked 41 prominent LLMs, aiming to bridge the existing cultural and linguistic evaluation gap in the field. The evaluation results are publicly available on our live leaderboard: https://huggingface.co/spaces/opll-org/Open-Persian-LLM-Leaderboard

MELAC: Massive Evaluation of Large Language Models with Alignment of Culture in Persian Language

We assess the capabilities of large language models on tasks involving Buddhist texts written in Sanskrit and Classical Tibetan—two typologically distinct, low-resource historical languages. To this end, we introduce DharmaBench, a benchmark suite comprising 13 classification and detection tasks grounded in Buddhist textual traditions: six in Sanskrit and seven in Tibetan, with four shared across both. The tasks are curated from scratch, tailored to the linguistic and cultural characteristics of each language. We evaluate a range of models, from proprietary systems like GPT-4o to smaller, domain-specific open-weight models, analyzing their performance across tasks and languages. All datasets and code are publicly released, under the CC-BY-4 License and the Apache-2.0 License respectively, to support research on historical language processing and the development of culturally inclusive NLP systems.

DharmaBench: Evaluating Language Models on Buddhist Texts in Sanskrit and Tibetan

We present a culturally-grounded multimodal dataset of 1,060 traditional recipes crowdsourced from rural communities across remote regions of Eastern India, spanning 10 endangered languages. These recipes, rich in linguistic and cultural nuance, were collected using a mobile interface designed for contributors with low digital literacy. Endangered Language Recipes (ELR)-1000---captures not only culinary practices but also the socio-cultural context embedded in indigenous food traditions. We evaluate the performance of several state-of-the-art large language models (LLMs) on translating these recipes into English and find the following: despite the models' capabilities, they struggle with low-resource, culturally-specific language. However, we observe that providing targeted context---including background information about the languages, translation examples, and guidelines for cultural preservation---leads to significant improvements in translation quality. Our results underscore the need for benchmarks that cater to underrepresented languages and domains to advance equitable and culturally-aware language technologies. As part of this work, we release the ELR-1000 dataset to the NLP community, hoping it motivates the development of language technologies for endangered languages.

ELR-1000: A Community-Generated Dataset for Endangered Indic Indigenous Languages

To alleviate the high cost of manually annotating Question Answering (QA) datasets, Question Generation (QG) requires the model to generate a question related to the given answer and passage. This work primarily focuses on Multi-Span Question Generation (MSQG), where the generated question corresponds to multiple candidate answers. Existing QG methods may not suit MSQG as they typically overlook the correlation between the candidate answers and generate trivial questions, which limits the quality of the synthetic datasets. Based on the observation that relevant entities typically share the same relationship with the same entity, we propose REGULAR, a framework of RElation-GUided MuLti-SpAn Question GeneRation. REGULAR first converts passages into relation graphs and extracts candidate answers from the relation graphs. Then, REGULAR utilizes a QG model to generate a set of candidate questions and a QA model to obtain the best question. We construct over 100,000 questions using Wikipedia corpora, named REGULAR-WIKI, and conduct experiments to compare our synthetic datasets with other synthetic QA datasets. The experiment results show that models trained with REGULAR-WIKI achieve the best performance. We also conduct ablation studies and statistical analysis to verify the quality of our synthetic dataset. Our code and data are available at {https://github.com/PluseLin/REGULAR.

REGULAR: A Framework for Relation-Guided Multi-Span Question Generation

Table understanding requires structured, multi-step reasoning. Large Language Models (LLMs) struggle with it due to the structural complexity of tabular data. Recently, multi-agent frameworks for SQL generation have shown promise in tackling the challenges of understanding tabular data, but existing approaches often suffer from limitations such as the inability to comprehend table structure for reliable SQL generation, error propagation that results in invalid queries, and over-reliance on execution correctness. To address these issues, we propose Chain-of-Query (CoQ), a novel multi-agent framework for SQL-aided table understanding. CoQ adopts natural-language-style representations of table schemas to abstract away structural noise and enhance understanding. It employs a clause-by-clause SQL generation strategy to improve query quality and introduces a hybrid reasoning division that separates SQL-based mechanical reasoning from LLM-based logical inference, thereby reducing reliance on execution outcomes. Extensive experiments across four models and five widely used benchmarks demonstrate that CoQ achieves substantial accuracy improvements and significantly lowers invalid SQL rates compared to prior generic LLM-based, SQL-aided, and hybrid baselines, confirming its superior effectiveness in table understanding. The code is available at https://github.com/SongyuanSui/ChainofQuery.

Chain-of-Query: Unleashing the Power of LLMs in SQL-Aided Table Understanding via Multi-Agent Collaboration

Existing benchmarks for frontier models often test specialized, "PhD-level" knowledge that is difficult for non-experts to grasp. In contrast, we present a benchmark with 613 problems based on the NPR Sunday Puzzle Challenge that requires only general knowledge. Our benchmark is challenging for both humans and models; however correct solutions are easy to verify, and models' mistakes are easy to spot. As LLMs are more widely deployed in society, we believe it is useful to develop benchmarks for frontier models that humans can understand without the need for deep domain expertise.

Our work reveals capability gaps that are not evident in existing benchmarks: OpenAI o1 significantly outperforms other reasoning models on our benchmark, despite being on par with other models when tested on benchmarks that test specialized knowledge. Furthermore, our analysis of reasoning outputs uncovers new kinds of failures. DeepSeek R1, for instance, often concedes with "I give up" before providing an answer that it knows is wrong. R1 can also be remarkably "uncertain" in its output and in rare cases, it does not "finish thinking," which suggests the need for techniques to ``wrap up'' before the context window limit is reached. We also quantify the effectiveness of reasoning longer to identify the point beyond which more reasoning is unlikely to improve accuracy on our benchmark.

ReasoningWeekly: A General Knowledge and Verbal Reasoning Challenge for Large Language Models

The increasing volume and complexity of Indian High Court judgments require high-quality automated summarization systems. Our agentic workflow framework for the summarization of Indian High Court judgments achieves competitive results without model fine-tuning. Experiments on CivilSum and IN-Abs test sets report ROUGE-1 F1 up to 0.547 and BERTScore F1 up to 0.866, comparable to state-of-the-art supervised models, with advantages in transparency and efficiency. We introduce two zero-shot modular agentic workflows: Lexical Modular Summarizer (LexA), a three-stage modular architecture optimized for lexical overlap (ROUGE), and Semantic Agentic Summarizer (SemA), a five-stage integrated architecture optimized for semantic similarity (BERTScore). Both workflows operate without supervised model fine-tuning, instead relying on strategic data processing, modular agent orchestration, and carefully engineered prompts. Our framework achieves ROUGE-1 F1 of 0.6326 and BERTScore F1 of 0.8902 on CivilSum test set, and ROUGE-1 F1 of 0.1951 and 
BERTScore F1 of 0.8299 on IN-Abs test set, substantially outperforming zero-shot baselines, rivaling leading fine-tuned transformer models while requiring no supervised training. This work demonstrates that modular, zero-shot agentic approaches can deliver production-grade results for legal summarization, offering a new direction for resource-limited judicial settings.

Legal Document Summarization: A Zero-shot Modular Agentic Workflow Approach

Despite comprehensive food safety regulations worldwide, violations continue to pose significant public health challenges. This paper presents an LLM-driven pipeline for analyzing legal texts to identify structural and procedural gaps in food safety enforcement. We develop an end-to-end system that leverages Large Language Models to extract structured entities from legal judgments, construct statute-and-provision-level knowledge graphs, and perform semantic clustering of cases. Applying our approach to $782$ Indian food safety violation cases filed between 2022-2024, we uncover critical insights: $96\%$ of cases were filed by individuals and organizations against state authorities, with $60\%$ resulting in decisions favoring appellants. Through automated clustering and analysis, we identify major procedural lapses including unclear jurisdictional boundaries between enforcement agencies, insufficient evidence collection, and ambiguous penalty guidelines. Our findings reveal concrete weaknesses in current enforcement practices and demonstrate the practical value of LLMs for legal analysis at scale.

LLM Driven Legal Text Analytics: A Case Study For Food Safety Violation Cases

The shared task of Legal Summarization (L-Summ) focuses on generating abstractive summaries for the Indian court judgments in English. This task presents unique challenges in producing fluent, relevant, and legally appropriate summaries given voluminous judgment texts. We experiment with different sequence-to-sequence models and present a comprehensive comparative study of their performance. We also evaluate various Large Language Models (LLM) with zero-shot settings for testing their summarization capabilities. Our best performing model is fine-tuned on a pre-trained legal summarization model where relevant passages are identified using the maximum marginal relevance(MMR) technique. Our findings highlight that retrieval-augmented fine-tuning is an effective approach for generating precise and concise legal summaries. We obtained a rank of 5th overall.

NIT-Surat@L-Sum: A Semantic Retrieval-Based Framework for Summarizing Indian Judicial Documents

In recent years, the research and development of large language models (LLMs) has been dominated by a small number of private organizations, largely conducted in a closed manner, and been predominantly English centric. Although some leading companies, such as Meta and DeepSeek, have adopted more open-source strategies than their competition, their training data and development processes remain closed to the wider scientific community and society as a whole. This closedness and at best limited transparency leads to an inability of the great majority of us to investigate and explore key scientific and societal challenges associated with this emerging technology, such as adapting and evaluating it for our own languages and exploring and addressing known issues such as biases and hallucinations. To address this, the LLM-jp project was launched in May 2023 under the leadership of the National Institute of Informatics as a sovereign, open, and collaborative initiative. Our aim is to develop Japanese-competent LLMs, elucidate the mechanisms behind their capabilities, and openly release all models, datasets, tools, and even share our discussions and failures with the public. Anyone who shares this vision is invited to participate, making LLM-jp an example of truly open and team science with more than 2,400 members to date.

The project is structured as a Big Science effort, bringing together multiple working groups covering corpus construction, model training, tuning and evaluation, safety, multimodal processing, and real-world applications. More than a dozen leading Japanese researchers from both universities and research institutes collaborate closely, supported by large-scale, national computational infrastructure, in alignment with emerging global AI safety initiatives, and with governmental support from the Ministry of Education, Culture, Sports, Science, and Technology.

In this keynote, I will present the motivations, organization, and progress of LLM-jp, and discuss how building a sovereign LLM ecosystem can not only advance Japan’s academic and industrial prowess, but also contribute to a global movement toward open and transparent AI research.

Downloads

Next from IJCNLP-AACL 2025

MELAC: Massive Evaluation of Large Language Models with Alignment of Culture in Persian Language

Similar lecture

MILDSum: A Novel Benchmark Dataset for Multilingual Summarization of Indian Legal Case Judgments

.css-70qvj9{display:-webkit-box;display:-webkit-flex;display:-ms-flexbox;display:flex;-webkit-align-items:center;-webkit-box-align:center;-ms-flex-align:center;align-items:center;}Downloads

Next from IJCNLP-AACL 2025

MELAC: Massive Evaluation of Large Language Models with Alignment of Culture in Persian Language

Similar lecture

MILDSum: A Novel Benchmark Dataset for Multilingual Summarization of Indian Legal Case Judgments

Downloads