ECPO: Evidence-Coupled Policy Optimization for Evidence-Certified Candidate Ranking

• URL: http://arxiv.org/abs/2605.21993v1
• Date: Thu, 21 May 2026 04:42:34 GMT
• Title: ECPO: Evidence-Coupled Policy Optimization for Evidence-Certified Candidate Ranking
• Abstract summary: We introduce Evidence-Coupled Policy Optimization (ECPO), a listwise policy-optimization objective whose action is the joint object of ranking and evidence certificate.<n>ECPO learns an interpretable trajectory reward from skeleton alignment, argument consistency, and optional graph features.<n>It then optimize a constrained policy with three coupled rewards: listwise ranking utility, span-level certificate validity, and an evidence-cycle reward computed by a label-free deterministic verifier.
• Score: 21.792889952064527
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Ranking systems used in decision-support settings should not only order candidates but also expose evidence that can be independently checked. We study evidence-certified candidate ranking: given an intent_id, a predefined plan skeleton, a window-local candidate roster, and text-derived candidate trajectories with span provenance, a system must output a Top-K list together with doc_id:span evidence certificates whose cited spans are sufficient to recover the decision. We instantiate this task on MAVEN-ERE and RAMS with fixed upstream extraction, window-local randomized candidate identifiers, skeleton-aligned trajectory supervision, hard negatives, and audit references. We introduce Evidence-Coupled Policy Optimization (ECPO), a listwise policy-optimization objective whose action is the joint object of ranking and evidence certificate. ECPO first learns an interpretable trajectory reward from skeleton alignment, argument consistency, and optional graph features; it then optimizes a constrained policy with three coupled rewards: listwise ranking utility, span-level certificate validity, and an evidence-cycle reward computed by a label-free deterministic verifier that reconstructs candidate support from claim-stripped cited spans. This reframes the goal from maximizing ordinary NDCG alone to maximizing CertNDCG and decision-evidence coupling. The evaluation compares ECPO against zero-shot, SFT, and GRPO policies, RM-only scoring with deterministic evidence attachment, grammar/JSON-constrained decoding, validator retry, best-of-N RM selection, and post-hoc evidence rationalization under closed-roster, predicted-roster, and hybrid-roster settings.

Related papers

• CVE-SAI: Counterfactual Visual Evidence-Guided Selective Attribute Indexing for Risk-Controlled E-commerce Search [12.763061404384601]
  Multimodal product models can complete missing e-commerce attributes.<n>Current methods still optimize attribute-answer accuracy, conflate transient prediction with persistent index admission.<n>We address these gaps with Counterfactual Visual Evidence-Guided Selective Attribute Distortioning.
  arXiv  Detail & Related papers  (2026-08-25T18:10:36Z)
• HARP: Hierarchical Adaptive Ranking with Preference-Adaptive Fusion for Query-Based CVE Prioritization [84.9738509922482]
  We propose a graph-grounded multi-view framework that ranks candidates from a natural-language query together with a support bank of historical labeled examples.<n>HarP retrieves evidence from a vulnerability knowledge graph, scores candidates with policy-conditioned global, enterprise, and user views, and fits view-fusion weights from sampled supports.
  arXiv  Detail & Related papers  (2026-08-19T20:29:00Z)
• RRPO: Reference-Relative Policy Optimization with Stratified Conditional Rollouts [84.20747697259326]
  Group Relative Policy Optimization (GRPO) has shown strong effectiveness in reinforcement learning from verifiable feedback.<n>We propose textbfReference-Relative Policy Optimization (RRPO), which generalizes GRPO by replacing direct correctness-based advantage construction with reference-relative contrastive comparisons.<n>We evaluate RRPO using anchor-based contrastive advantages throughout policy optimization, without relying on task ground-truth verifiers.
  arXiv  Detail & Related papers  (2026-07-20T19:40:25Z)
• Candidate-Constrained Retrieval-Augmented Generation for LongEval-RAG: System Design and Empirical Analysis [1.0312968200748118]
  We present a candidate-constrained retrieval-augmented generation system for LongEval-RAG.<n>We evaluate ten pipeline variants using a primary organizer evaluation and a supplementary self-generated diagnostic protocol.
  arXiv  Detail & Related papers  (2026-07-04T20:07:57Z)
• Distributionally Robust Listwise Preference Optimization [47.053005334474896]
  We study listwise preference optimization under ranking-label uncertainty.<n>We propose a pointwise total-variation robust Plackett--Luce objective that directly robustifies the ranking label conditional on the candidate list.<n> Experiments show that the proposed robust correction largely preserves performance under clean labels and improves robustness under noise.
  arXiv  Detail & Related papers  (2026-07-02T05:12:03Z)
• Beyond Static Leaderboards: Predictive Validity for the Evaluation of LLM Agents [19.290397279235084]
  This paper aggregates the largest coordinated deep-dive of one MCP-based industrial-agent benchmark to date.<n>We argue that aggregate-score leaderboards systematically underspecify deployed-agent evaluation.
  arXiv  Detail & Related papers  (2026-06-18T02:02:46Z)
• CriterAlign: Criterion-Centric Rationale Alignment for Code Preference Judging [95.02210956333374]
  We propose a criterion-centric framework that adapts rubric-based judging to pairwise preference evaluation.<n>On BigCodeReward, CriterAlign improves a Qwen2.5-VL-32B monolithic judge from 60.4% to 66.3% accuracy.
  arXiv  Detail & Related papers  (2026-05-19T10:59:19Z)
• F-GRPO: Factorized Group-Relative Policy Optimization for Unified Candidate Generation and Ranking [79.49893545611779]
  Large Language Models (LLMs) can generate a subset and order it within a single autoregressive pass.<n>This flexibility introduces a new optimization challenge: the model must search an output space while receiving utility feedback only after the full ranked list is generated.<n>This credit assignment gap makes end-to-end optimization unstable and sample-inefficient.<n>We propose a unified framework that performs both within a single autoregressive rollout and optimize them end-to-end via factorized group-relative policy optimization.
  arXiv  Detail & Related papers  (2026-05-13T04:52:33Z)
• GEM: Guided Expectation-Maximization for Behavior-Normalized Candidate Action Selection in Offline RL [7.213487945222728]
  We introduce GEM (Guided Expectation-Maximization), an analytical framework that makes action selection both multimodal and controllable.<n>During inference, GEM performs candidate-based selection using a conservative ensemble lower-confidence bound together with behavior-normalized support.<n> Empirically, GEM is competitive across D4RL benchmarks, and offers a simple inference-time budget knob (candidate count) that trades compute for decision quality without retraining.
  arXiv  Detail & Related papers  (2026-03-24T14:04:43Z)
• DARC: Disagreement-Aware Alignment via Risk-Constrained Decoding [59.16244104797919]
  We propose **Disagreement-Aware Alignment via Risk-Constrained Decoding (DARC)**.<n>DARC frames response selection as distributionally robust, risk-sensitive decision making.<n>Experiments on alignment benchmarks show that DARC reduces disagreement and tail risk while maintaining competitive average quality.
  arXiv  Detail & Related papers  (2026-03-09T09:21:29Z)
• Evidence-Augmented Policy Optimization with Reward Co-Evolution for Long-Context Reasoning [52.144281362465996]
  We propose EAPO (Evidence-Augmented Policy Optimization) to apply Reinforcement Learning to long-context scenarios.<n>We first establish the Evidence-Augmented Reasoning paradigm, validating via Tree-Structured Evidence Sampling.<n>We then introduce a specialized RL algorithm where a reward model computes a Group-Relative Evidence Reward.<n>To sustain accurate supervision throughout training, we further incorporate an Adaptive Reward-Policy Co-Evolution mechanism.
  arXiv  Detail & Related papers  (2026-01-15T11:40:57Z)
• RLPO: Residual Listwise Preference Optimization for Long-Context Review Ranking [50.709454968853954]
  Pointwise scoring is efficient but often fails to account for list-level interactions.<n>Listwise approaches can leverage global context, yet they are computationally expensive and become unstable as candidate lists grow.<n>We propose Residual Listwise Preference Optimization (RLPO), which formulates ranking as listwise representation-level residual correction.
  arXiv  Detail & Related papers  (2026-01-12T11:45:19Z)
• Ranking Free RAG: Replacing Re-ranking with Selection in RAG for Sensitive Domains [13.58151841630302]
  We propose a novel method METEORA that replaces re-ranking in RAG with a rationale-driven selection approach.<n>We show METEORA improves generation accuracy by 33.34% while using approximately 50% fewer chunks than state-of-the-art re-ranking methods.<n>In adversarial settings, METEORA significantly improves the F1 score from 0.10 to 0.44.
  arXiv  Detail & Related papers  (2025-05-21T20:57:16Z)
• Recommendation Systems with Distribution-Free Reliability Guarantees [83.80644194980042]
  We show how to return a set of items rigorously guaranteed to contain mostly good items. Our procedure endows any ranking model with rigorous finite-sample control of the false discovery rate. We evaluate our methods on the Yahoo! Learning to Rank and MSMarco datasets.
  arXiv  Detail & Related papers  (2022-07-04T17:49:25Z)

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.