arXiv AI
Jul 22
FinRAG-12B: A Production-Validated Recipe for Grounded Question Answering in Banking
arXiv:2605. 05482v2 Announce Type: replace Abstract: Large language models (LLMs) are rapidly being adopted across various domains.
Automated Regulatory Compliance Question Answering in Financial Services with Domain-Adapted Retrieval-Augmented Generation
The paper presents a retrieval‑augmented generation pipeline for answering regulatory compliance questions in finance. It builds a three‑stage retriever on LegalBERT and a compact 2B–12B generator served with 4‑bit quantization, achieving a Recall@10 of 0.774 on the ObliQA benchmark and improving answer quality via RAFT‑LoRA fine‑tuning. However, the adapted models fail to transfer to Australian case‑law questions, and a closed‑book model performs almost as well while lacking verifiable grounding.
Related stories
arXiv AI
Sep 4
Enhancing Financial Question Answering: A Novel Benchmark Dataset of Banks' financial statements
FinRAG-QA is a new benchmark dataset for financial question answering, featuring 999 practitioner-curated questions on 10 standardised indicators drawn from 209 annual and Pillar 3 reports of 24 major European and U.S. banks between 2019 and 2023. The dataset focuses on cross‑institutional retrieval over documents averaging 198k words, making it longer than any existing financial QA resource. Experiments on a multi‑stage Retrieval‑Augmented Generation pipeline show that contextual chunk enrichment and a retrieval‑optimised embedding model significantly improve NDCG@10, while a reasoning‑optimised generator boosts answer accuracy from 44.6% to 79.0% when the correct document is retrieved.
arXiv AI
Aug 11
Temporal Misgrounding in Legal RAG: A Versioned-Corpus Benchmark for French Tax Law
arXiv:2608. 09393v1 Announce Type: cross Abstract: We identify and quantify temporal misgrounding: the systematic retrieval and citation of the currently in-force version of a legal article when the applicable version is an earlier or future one.
arXiv AI
Jul 7
Agentic Retrieval-Augmented Generation for Financial Document Question Answering
arXiv:2605. 05409v2 Announce Type: replace Abstract: Financial document question answering (QA) demands complex multi-step numerical reasoning over heterogeneous evidence--structured tables, textual narratives, and footnotes--scattered across corporate filings.
arXiv AI
Jul 29
Beyond Self-Knowledge: Propagating Uncertainty Across Reasoning and Retrieval in LLMs
arXiv:2607. 25600v1 Announce Type: cross Abstract: Retrieval-augmented generation improves knowledge-intensive question answering, but indiscriminate retrieval can introduce irrelevant evidence and unnecessary computation.
arXiv AI
Aug 24
Clarify-Then-Search: A Clarification Benchmark for Deep Search with End-to-End Nugget Restoration
Clarify-Then-Search is a benchmark that tests whether large language models can ask clarification questions to improve the usefulness of deep search results. It uses 518 real-world query pairs from Baidu, where each intent query is paired with an underspecified version. The evaluation involves a clarifier asking up to three questions, a user answerer providing only explicit information, and a rewriter generating a new query that is then searched; performance is measured by a weighted nugget-recall score.
arXiv AI
Aug 18
Think Inside the Chunk: RegulaRAG for Regulation-Compliant Scenario Generation using LLMs: A Case Study of UN Regulation No. 152
arXiv:2608. 16394v1 Announce Type: new Abstract: Generating regulation-compliant test scenarios is essential for validating safety-critical automotive systems, yet Large Language Models (LLMs) struggle to ground outputs in long, hierarchical standards.
arXiv Computation and Language
Sep 22
Efficient LLM Distillation for Bangladesh Legal Context: A Smartphone-Compatible Retrieval-Augmented Generation Model
The paper presents a smartphone‑compatible, retrieval‑augmented language model tailored to Bangladeshi statutory law. By distilling a 9‑billion‑parameter Gemma‑2 teacher into a 2‑billion‑parameter student using supervised fine‑tuning and QLoRA, the authors achieve significant gains in ROUGE‑L and BERTScore on an English benchmark while keeping the model lightweight (1.6 GB) and operable offline on a Pixel 6. The system retrieves from 36,029 statutory passages using a hybrid dense/BM25 approach, and cross‑lingual evaluation shows effective Bangla query handling against an English‑only corpus, with a practicing lawyer rating the responses highly in a pilot study.
Hugging Face Trending Papers
Jul 21
RAGAL: A Frugal, Fully Local Retrieval-Augmented Assistant for Technical Support at a Government Agency
Public institutions hold large volumes of sensitive documents and support tickets that cannot leave the premises, ruling out cloud-hosted language models entirely. We report on RAGAL, a retrieval-augmented assistant for the technical-support team of AFIR, the Romanian Agency for Financing Rural Investments, built and operated under three hard constraints: zero data egress (no external API calls, even for synthetic data), a read-only mandate (the assistant drafts, humans execute), and a single 8 GB consumer laptop as the only development and training machine.
arXiv AI
Aug 21
Inject, Align, Recover: Staged Post-Training for Retrieval-Free Document Knowledge Internalization
arXiv:2608. 20281v1 Announce Type: cross Abstract: Large language models often fail to answer questions about a bounded document collection when the source documents are not retrieved at inference time.
arXiv AI
Aug 11
Bounding Hallucinations: Merlin-Arthur Protocols for Mutual-Information Bounds in Language Models
arXiv:2512. 11614v3 Announce Type: replace-cross Abstract: Retrieval-augmented generation (RAG) relies on retrieved context to guide large language models (LLM), yet treats the retrieval as a heuristic rather than verifiable evidence -- leading to unsupported answers, hallucinations, and reliance on spurious context.
arXiv AI
2d ago
Regime Boundary Alignment for Evidence-Gated Question Answering
arXiv:2609.37491v1 Announce Type: cross Abstract: Retrieval-augmented language models are expected to answer from the retrieved evidence, but in practice they often keep answering when that evidence...