Explainable AML Triage with LLMs: Evidence Retrieval and Counterfactual Checks

• URL: http://arxiv.org/abs/2604.19755v1
• Date: Sun, 22 Mar 2026 05:51:40 GMT
• Title: Explainable AML Triage with LLMs: Evidence Retrieval and Counterfactual Checks
• Abstract summary: We propose an explainable AML triage framework that treats triage as an evidence-constrained decision process.<n>Our method combines (i) retrieval-augmented evidence bundling from policy/typology guidance, customer context, alert triggers, and transaction subgraphs, (ii) a structured LLM output contract that requires explicit citations and separates supporting from contradicting or missing evidence, and (iii) counterfactual checks that validate whether minimal, plausible perturbations lead to coherent changes in both the triage recommendation and its rationale.
• Score: 19.272001035427987
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Anti-money laundering (AML) transaction monitoring generates large volumes of alerts that must be rapidly triaged by investigators under strict audit and governance constraints. While large language models (LLMs) can summarize heterogeneous evidence and draft rationales, unconstrained generation is risky in regulated workflows due to hallucinations, weak provenance, and explanations that are not faithful to the underlying decision. We propose an explainable AML triage framework that treats triage as an evidence-constrained decision process. Our method combines (i) retrieval-augmented evidence bundling from policy/typology guidance, customer context, alert triggers, and transaction subgraphs, (ii) a structured LLM output contract that requires explicit citations and separates supporting from contradicting or missing evidence, and (iii) counterfactual checks that validate whether minimal, plausible perturbations lead to coherent changes in both the triage recommendation and its rationale. We evaluate on public synthetic AML benchmarks and simulators and compare against rules, tabular and graph machine-learning baselines, and LLM-only/RAG-only variants. Results show that evidence grounding substantially improves auditability and reduces numerical and policy hallucination errors, while counterfactual validation further increases decision-linked explainability and robustness, yielding the best overall triage performance (PR-AUC 0.75; Escalate F1 0.62) and strong provenance and faithfulness metrics (citation validity 0.98; evidence support 0.88; counterfactual faithfulness 0.76). These findings indicate that governed, verifiable LLM systems can provide practical decision support for AML triage without sacrificing compliance requirements for traceability and defensibility.

Related papers

• Mitigating LLM Sycophancy in Code Smell Detection Using Evidence-Guided Reasoning Prompts [0.0]
  We present the first systematic empirical study of sycophancy bias in large language models.<n>We show that sycophancy bias poses a critical threat to the reliability of LLM-based code smell detection.<n>We propose Evidence-Guided Debiasing Prompting (EGDP), a structured prompting strategy that enforces evidence-first reasoning.
  arXiv  Detail & Related papers  (2026-07-11T17:35:25Z)
• Time to REFLECT: Can We Trust LLM Judges for Evidence-based Research Agents? [61.49434544687523]
  We introduce REFLECT, a meta-evaluation benchmark targeting fine-grained failure detection in agentic environments.<n> REFLECT defines a detailed taxonomy of process- and outcome-level failure modes, instantiated by performing controlled and localized interventions.<n>Our experiments show that even the best-performing models achieve overall accuracies below 55% across reasoning, tool-use, and report-quality failures.
  arXiv  Detail & Related papers  (2026-05-18T23:55:08Z)
• Representation Signatures and Risk-Feedback Alignment in LLM Trading Agents [0.0635655952373977]
  We study behavioral alignment and representation dynamics of large language model (LLM) agents in financial decision environments.<n>We find that planning embeddings drift from normal-state centroids, fused plan-risk representations separate normal from pre-drawdown states, and diagnostics show effective-rank contraction before failures.<n>We also find that structured risk feedback can act as an external alignment signal without fine-tuning, but not as a universal performance enhancer.
  arXiv  Detail & Related papers  (2026-05-16T16:53:34Z)
• Logic-Regularized Verifier Elicits Reasoning from LLMs [63.65875399266337]
  We propose LOVER, an unsupervised verifier regularized by logical rules.<n>Lover treats theverifier as a binary latent variable, utilizinginternal activations and enforcing three logical constraints.<n>Lover significantly outperforms unsupervised baselines.
  arXiv  Detail & Related papers  (2026-05-07T09:03:49Z)
• Safeguarding LLM Agents from Misalignment through Provenance Analysis [4.942326117464286]
  Existing runtime guardrails rely on an LLM-as-a-judge paradigm.<n>We propose a provenance-based conceptual framework that formalizes misalignment detection.<n>ProvenanceGuard reduces error rate on misaligned traces from 42.9% to 1.8% on Agent-SafetyBench and from 32.1% to 17.3% on WorkBench.
  arXiv  Detail & Related papers  (2026-05-01T03:16:35Z)
• Trust but Verify: Introducing DAVinCI -- A Framework for Dual Attribution and Verification in Claim Inference for Language Models [53.279391576560755]
  Large Language Models (LLMs) have demonstrated remarkable fluency and versatility across a wide range of NLP tasks, yet they remain prone to factual inaccuracies and limitation.<n>This poses significant risks in high-stakes domains such as healthcare, law, and scientific communication, where trust and verifiability are paramount.<n>We introduce DAVinCI - a Dual Attribution and Verification framework designed to enhance the factual reliability and interpretability of LLM outputs.
  arXiv  Detail & Related papers  (2026-04-23T01:37:50Z)
• MARCH: Multi-Agent Reinforced Self-Check for LLM Hallucination [25.50050557327127]
  Hallucination remains a critical bottleneck for large language models (LLMs)<n>We introduce Multi-Agent Reinforced Self-Check for Hallucination (MARCH)<n>MARCH enforces rigorous factual alignment by leveraging deliberate information asymmetry.
  arXiv  Detail & Related papers  (2026-03-25T17:54:10Z)
• Information Fidelity in Tool-Using LLM Agents: A Martingale Analysis of the Model Context Protocol [69.11739400975445]
  We introduce the first theoretical framework for analyzing error accumulation in Model Context Protocol (MCP) agents.<n>We show that cumulative distortion exhibits linear growth and high-probability deviations bounded by $O(sqrtT)$.<n>Key findings include: semantic weighting reduces distortion by 80%, and periodic re-grounding approximately every 9 steps suffices for error control.
  arXiv  Detail & Related papers  (2026-02-10T21:08:53Z)
• Gaming the Judge: Unfaithful Chain-of-Thought Can Undermine Agent Evaluation [76.5533899503582]
  Large language models (LLMs) are increasingly used as judges to evaluate agent performance.<n>We show this paradigm implicitly assumes that the agent's chain-of-thought (CoT) reasoning faithfully reflects both its internal reasoning and the underlying environment state.<n>We demonstrate that manipulated reasoning alone can inflate false positive rates of state-of-the-art VLM judges by up to 90% across 800 trajectories spanning diverse web tasks.
  arXiv  Detail & Related papers  (2026-01-21T06:07:43Z)
• Towards Comprehensive Stage-wise Benchmarking of Large Language Models in Fact-Checking [64.97768177044355]
  Large Language Models (LLMs) are increasingly deployed in real-world fact-checking systems.<n>We present FactArena, a fully automated arena-style evaluation framework.<n>Our analyses reveal significant discrepancies between static claim-verification accuracy and end-to-end fact-checking competence.
  arXiv  Detail & Related papers  (2026-01-06T02:51:56Z)
• HADSF: Aspect Aware Semantic Control for Explainable Recommendation [4.75127493865044]
  Recent advances in large language models (LLMs) promise more effective information extraction for recommender systems.<n>We propose a two-stage approach that induces a compact, corpus-level aspect vocabulary via adaptive selection and then performs vocabulary-guided, explicitly constrained extraction of structured aspect-opinion triples.<n> Experiments on approximately 3 million reviews spanning 1.5B-70B parameters show that, when integrated into standard rating predictors, HADSF yields consistent reductions in prediction error.
  arXiv  Detail & Related papers  (2025-10-30T20:49:33Z)
• Co-Sight: Enhancing LLM-Based Agents via Conflict-Aware Meta-Verification and Trustworthy Reasoning with Structured Facts [18.221173068008603]
  Co-Sight turns reasoning into a falsifiable and auditable process.<n>Two mechanisms: Conflict-Aware Meta-Verification (CAMV) and Trustworthy Reasoning with Structured Facts (TRSF)
  arXiv  Detail & Related papers  (2025-10-24T15:14:14Z)
• FactCHD: Benchmarking Fact-Conflicting Hallucination Detection [64.4610684475899]
  FactCHD is a benchmark designed for the detection of fact-conflicting hallucinations from LLMs. FactCHD features a diverse dataset that spans various factuality patterns, including vanilla, multi-hop, comparison, and set operation. We introduce Truth-Triangulator that synthesizes reflective considerations by tool-enhanced ChatGPT and LoRA-tuning based on Llama2.
  arXiv  Detail & Related papers  (2023-10-18T16:27:49Z)

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.