Searcharxiv⌕ Search
Home/Archive/arXiv

arXiv · 2508.04710

Augmented Question-guided Retrieval (AQgR) of Indian Case Law with LLM, RAG, and Structured Summaries

Vishnuprabha V·Daleesha M Viswanathan·Rajesh R·Aneesh V Pillai
View original source ↗Read source document ↗Export metadata ↓

Abstract

Identifying relevant legal precedents remains challenging, as most retrieval methods emphasize factual similarity over legal issues, and current systems often lack explanations clarifying case relevance. This paper proposes the use of Large Language Models (LLMs) to address this gap by facilitating the retrieval of relevant cases, generating explanations to elucidate relevance, and identifying core legal issues all autonomously, without requiring legal expertise. Our approach combines Retrieval Augmented Generation (RAG) with structured summaries optimized for Indian case law. Leveraging the Augmented Question-guided Retrieval (AQgR) framework, the system generates targeted legal questions based on factual scenarios to identify relevant case law more effectively. The structured summaries were assessed manually by legal experts, given the absence of a suitable structured summary dataset. Case law retrieval was evaluated using the FIRE dataset, and explanations were reviewed by legal experts, as explanation generation alongside case retrieval is an emerging innovation. Experimental evaluation on a subset of the FIRE 2019 dataset yielded promising outcomes, achieving a Mean Average Precision (MAP) score of 0.36 and a Mean Average Recall (MAR) of 0.67 across test queries, significantly surpassing the current MAP benchmark of 0.1573. This work introduces a suite of novel contributions to advance case law retrieval. By transitioning from fact-based to legal-issue-based retrieval, the proposed approach delivers more contextually relevant results that align closely with legal professionals' needs. Integrating legal questions within the retrieval process through the AQgR framework ensures more precise and meaningful retrieval by refining the context of queries.

Explore related subjects

cs.IR

Keep this discovery

BibTeXRIS

Vishnuprabha V, Daleesha M Viswanathan, Rajesh R, Aneesh V Pillai. 2025-07-23. Augmented Question-guided Retrieval (AQgR) of Indian Case Law with LLM, RAG, and Structured Summaries. https://arxiv.org/abs/2508.04710

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related papers

arXiv2026

UniRec: Cross-stage Multi-Task Fusion with Preference Alignment for Cascaded Recommender Systems

Industrial recommender systems use cascaded stages with different objectives, feature spaces, and latency constraints. Optimizing pre-ranking and ranking separately can create cross-stage inconsistency: upstream models may filter out items preferred by downstream rankers, and independently tuned downstream fusion can offset upstream improvements. Existing multi-task fusion methods focus on multi-objective fusion within the ranking stage, and cross-stage methods typically only add a downstream score factor to upstream ranking. Joint optimization of fusion modules across both stages remains largely unexplored. We propose UniRec, a Unified Cross-stage Recommendation Fusion model. First, the two fusion agents partially share input embeddings and are trained in a single computation graph, so gradients from either stage propagate through the shared representation and influence the other. Second, we introduce a dual-axis preference alignment objective: a vertical cross-stage consistency term transfers downstream pairwise preferences to the upstream fusion score, and a horizontal compact aggregation term reorganizes dozens of pairwise objectives over heterogeneous prior signals into bidirectional preference evidence. Third, we find that unconstrained end-to-end fusion optimization can exploit imbalances in item attribute distributions, over-concentrating on high-reward regions at the cost of other objectives. We therefore add an attribute group-relative regularization that computes advantages within attribute groups and normalizes the policy over the same groups, so uniformly promoting an entire high-reward group yields no optimization gain. Offline, UniRec consistently outperforms single-stage fusion and cross-stage coordination baselines. Online A/B tests show a 0.616\% gain in app usage duration. UniRec is fully deployed on the Kuaishou platform.

cs.IR↗
arXiv2026

VikingRAG: Accurate and Token-efficient Retrieval-augmented Generation over Structured Documents

State-of-the-art retrieval-augmented generation (RAG) methods exploit document structures to acquire sufficient evidence, but often incur substantial token costs. To reduce structural-context tokens without compromising high RAG accuracy, we present {\sf VikingRAG}, a directory-aware semantic data management system that tightly integrates semantic and structural access to support structural-context-efficient, evidence-gap-driven multi-round retrieval. To further reduce token overhead of multi-round interaction, we materialize agentic multi-round retrieval traces as experience edges, and reuse these edges for similar queries, avoiding repeated multi-round exploration. To additionally reduce token costs when agentic multi-round retrieval is unnecessary, we introduce an adaptive escalation strategy that answers from one-round experience-augmented retrieval when the evidence is sufficient, and invokes agentic multi-round retrieval only otherwise. Experiments on real datasets show that the base system {\sf VikingRAG} matches high accuracy of state-of-the-art methods while consuming only 11.6\%--51.9\% of their tokens. With retrieval-trace reuse and adaptive escalation, token costs drop to 5.1\%--32.5\% while maintaining competitive accuracy and practical document-storage performance, showing the utility of this work for emerging AI knowledge bases.

cs.IR↗
arXiv2026

TimelyRAG: Semantic-Temporal Hybrid Retrieval for Time-Critical Question Answering in Overlapping-Evolving Documents

Although large language models (LLMs) and retrieval-augmented generation (RAG) have advanced open-domain question answering (QA), they remain unreliable when documents evolve through amendments. Existing time-sensitive retrieval methods address only the disjoint-evolving environment, where each update is an independent snapshot. However, laws, policies, and regulations often operate in overlapping-evolving environments, where amendments override earlier clauses while preserving most content, creating strong semantic overlap across versions. We propose TimelyRAG, a retriever-agnostic framework that incorporates temporal distance into ranking to align queries with version-appropriate documents. We also introduce TimelyQABench, the first benchmark for regulation-heavy domains with overlapping-evolving challenges. Experiments show consistent gains, up to +28.6% in nDCG@10, highlighting the importance of temporal reasoning for reliable QA over evolving documents. All resources are available at https://github.com/kaist-dmlab/TimelyRAG.

cs.IR↗