GANDR: Claim Auditing for Verifiable Legal Answer Generation

• URL: http://arxiv.org/abs/2609.10293v1
• Date: Wed, 09 Sep 2026 15:08:09 GMT
• Title: GANDR: Claim Auditing for Verifiable Legal Answer Generation
• Abstract summary: Grounded-generation pipelines score the answer as a whole, so a correct conclusion can rest on fabricated or loosely matched citations and still score well.<n>We introduce GANDR, a two-agent system in which a Drafter writes an answer in a structured legal-reasoning format and a Critic, with the same view as a human verifier, audits each claim against its cited source.<n>On a 185-item legal benchmark, GANDR ranks first on every primary metric, reaching 70.8% strict accuracy and leading the strongest baseline by 11.3 points (p0.01)
• Score: 21.842813905857863
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: In high-stakes domains such as legal practice, a language-model answer is only useful to the extent that a reader can verify each claim against the source the system cites. Current grounded-generation pipelines score the answer as a whole, so a correct conclusion can rest on fabricated or loosely matched citations and still score well. Closing this gap requires both a system built for per-claim verification and an evaluation that measures it. We introduce GANDR (Grounded ANswer DRafter), a two-agent system in which a Drafter writes an answer in a structured legal-reasoning format and a separate Critic, with the same view as a human verifier, audits each claim against its cited source and emits a per-claim audit trace on every round. We pair it with a strict correctness criterion requiring every citation to resolve to a passage the retriever returned. On a 185-item legal benchmark where all six systems share one backbone, one retrieval surface, and one citation instruction, GANDR ranks first on every primary metric, reaching 70.8% strict accuracy and leading the strongest baseline by 11.3 points (p<0.01). Reverting the protocol-anchored commit rule lowers strict accuracy by 22.7 points, and the strict lead stays positive on three further backbones, at +3.2 to +6.5 points. This lead traces to the Drafter configuration and the protocol-anchored commit, not to rewriting. Against two law-trained annotators the audit flags under-supported claims at F1 0.84 as a binary detector, while its four-way verdict labels agree only weakly and are advisory. Code is available upon request.

Related papers

• AtomCite: Verification and Correction of Supplied Page-Level Citations in Multi-Page Documents [21.842813905857863]
  AtomCite parses an answer into claims, checks each claim against the image of the cited page, and applies a deterministic repair policy.<n>It reaches around 93% binary verification accuracy on the injected benchmark, significantly outperforming every OCR-only condition.<n>Its repair policy lifts citation precision on the injected mix from a constructed 34% to 87-90% while retaining over 90% of correct claims.
  arXiv  Detail & Related papers  (2026-09-05T01:31:50Z)
• ATIBA: Grounded Integrity and Quality Checking for Research Papers [1.3241176321860364]
  We present ATIBA, a tool that runs five grounded integrity and quality checks on a manuscript.<n>It is designed around the same principle: an LLM is only trusted to judge, never to invent the evidence it judges against.
  arXiv  Detail & Related papers  (2026-09-03T17:24:15Z)
• DualityCert: Verifier-Gated Language-Model Repair of Broken Duality Claims in Quantum Field Theory [0.0]
  We present DualityCert, a symbolic verifier for candidate Seiberg-duality claims in four-dimensional N=1 quiver gauge theories.<n>A claim that passes receives a consistency certificate, which states that no tested inconsistency was found, not that the duality is proven.<n>We use the verifier as a repair environment for language-model agents, which receive a deliberately broken claim and must edit it until it certifies.
  arXiv  Detail & Related papers  (2026-07-26T11:39:49Z)
• Two Regimes of Chain-of-Thought Unfaithfulness: Behavioral Detection Fails Where Models Are Wrong [1.2744523252873352]
  Black-box (behavioral) detection of unfaithful CoT against FaithCoT-Bench's human annotations.<n>We find answer correctness structures the problem at every level.
  arXiv  Detail & Related papers  (2026-07-26T04:43:53Z)
• Fantastic Adaptive Taxonomies and How to Use Them [100.20614173157708]
  AdaMAST converts execution traces into a compact, evidence-grounded failure taxonomy.<n>No code is hand-authored, no trace human-annotated.<n>In agent-system search, taxonomy-coded diagnoses of failed candidates outperform free-form.
  arXiv  Detail & Related papers  (2026-07-17T17:41:16Z)
• FineVerify: Scaling Test-Time Compute with Fine-Grained Self-Verification for Agentic Search [88.16262636915975]
  FineVerify is a fine-grained self-verification framework for agentic search.<n>It decomposes each question into checkable sub-questions, verifies sampled candidates, and selects the candidate with the highest aggregated score.<n>FineVerify consistently outperforms standard scaling baselines.
  arXiv  Detail & Related papers  (2026-05-30T10:21:20Z)
• Citation-Closure Retrieval and Per-Rule Attribution for Real-World Regulatory Compliance Question Answering [54.97384993676565]
  We formalize Regulatory Compliance QA with RegOps-Bench, a novel benchmark featuring an Operational Knowledge Graph derived from complex national R&D regulations.<n>RefWalk traverses cross-document citations, fuses multi-view candidates via max-based aggregation, and enforces per-rule attribution to explicitly map claims to sources.
  arXiv  Detail & Related papers  (2026-05-28T10:38:38Z)
• SURE-RAG: Sufficiency and Uncertainty-Aware Evidence Verification for Selective Retrieval-Augmented Generation [6.604874054866016]
  We present SURE-RAG, a transparent aggregation protocol built on the observation that evidence sufficiency is a set-level property.<n>A shared pair-level claim-evidence verifier produces local relation distributions, which SURE-RAG aggregates into interpretable answer-level signals.<n>We evaluate on HotpotQA-RAG v3, a controlled multi-hop benchmark, under an artifact-aware protocol.
  arXiv  Detail & Related papers  (2026-05-05T09:05:40Z)
• CARE What Fails: Contrastive Anchored-REflection for Verifiable Multimodal [84.71254539482369]
  Group-relative reinforcement learning with verifiable rewards (RLVR) often wastes the most informative data it already has the failures.<n>We present CARE, a failure-centric post-training framework for multimodal reasoning that turns errors into supervision.<n> CARE improves accuracy and training smoothness while explicitly increasing the share of learning signal that comes from failures.
  arXiv  Detail & Related papers  (2025-12-22T16:34:21Z)
• Reinforcement Learning with Verifiable yet Noisy Rewards under Imperfect Verifiers [90.50039419576807]
  Reinforcement Learning with Verifiable Rewards (RLVR) trains policies against automated verifiers to avoid costly human labeling.<n>To reduce vulnerability to verifier hacking, many RLVR systems collapse rewards to binary $0,1$ during training.<n>This choice carries a cost: it introduces textitfalse negatives (rejecting correct answers, FNs) and textitfalse positives (accepting incorrect ones, FPs)
  arXiv  Detail & Related papers  (2025-10-01T13:56:44Z)
• End-to-End Page-Level Assessment of Handwritten Text Recognition [69.55992406968495]
  HTR systems increasingly face the end-to-end page-level transcription of a document. Standard metrics do not take into account the inconsistencies that might appear. We propose a two-fold evaluation, where the transcription accuracy and the RO goodness are considered separately.
  arXiv  Detail & Related papers  (2023-01-14T15:43:07Z)

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.