Cherry-pick Override: Unsafe Directional Commitment in LLM Judges under Mixed Evidence

• URL: http://arxiv.org/abs/2606.07834v1
• Date: Fri, 05 Jun 2026 20:51:51 GMT
• Title: Cherry-pick Override: Unsafe Directional Commitment in LLM Judges under Mixed Evidence
• Abstract summary: We argue for an external commitment-control layer that separates verdict generation from commitment authorization.<n>We define CCO under an explicit task contract and report it with a same-denominator diagnostic protocol.
• Score: 14.905172804386973
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: LLM judges increasingly turn verdicts into system commitments. Under mixed evidence (claims with both supporting and refuting sources) this is unsafe: when the schema exposes CONFLICTING as the authorized non-directional verdict, returning SUPPORTS/REFUTES is an unauthorized directional commitment, a failure we name Cherry-pick Override (CCO). We define CCO under an explicit task contract and report it with a same-denominator diagnostic protocol paired with matched-coverage bootstrap and an apples-to-apples random-veto null. On AVeriTeC's Conflicting subset (N_C = 150), three-option judges return a directional verdict on more than 84% of mixed-evidence claims; under the typed schema, three-judge majority voting amplifies direction-on-conflict on AVeriTeC (0.887 vs. 0.840; 95% CI [+0.013, +0.080]) but does not replicate on VitaminC-Mixed. Walking an intervention ladder of common single-channel fixes (typed vocabulary, panel aggregation, confidence thresholding, validator-only filtering), each leaves a distinct residual failure: panel aggregation suppresses single-judge CONFLICTING dissent in 48% of CCO cases; the panel is well-calibrated for direction (ECE = 0.07 on pure-S/R) so confidence cannot operationally separate CCO from correct directional commits; validator-as-classifier nearly halves pure-evidence accuracy. A minimal two-channel reference probe reaches operating points neither single channel reaches; under the random-veto null its promotion to CONFLICTING is structurally targeted on AVeriTeC (empirical p < 1/2001) and weaker but in the same direction on VitaminC-Mixed, a selectivity result rather than a magnitude one. We argue for an external commitment-control layer that separates verdict generation from commitment authorization, using structural evidence and confidence as orthogonal channels and NO-COMMIT as a routed controller state.

Related papers

• Unmatched Does Not Mean False: Incomplete Reference Sets Can Reverse Calibration Rankings in Open-Ended Theory-of-Mind Tracking [0.5735035463793009]
  Open-ended Theory-of-Mind (ToM) trackers emit valid beliefs absent from finite references.<n>A finite-reference-plus-matcher pipeline marks unmatched outputs false, creating proxy labels that can reverse proper-score model selection.
  arXiv  Detail & Related papers  (2026-08-26T11:36:31Z)
• Credit Without Ground Truth: Auditing Step-Level Credit Assignment in LLM Agents Against Executed Replay [0.6768558752130311]
  We audit against policy-conditional ground truth from executed replay in a single-agent tool environment.<n>No step-level credit signals we audit show reliable incremental fidelity beyond marginal-matched shuffled control.<n>A confidence-only router recovers pivotal steps at chance level, but cuts judge cost by 13.1% per turn.
  arXiv  Detail & Related papers  (2026-08-20T08:04:00Z)
• Cross-Fitted Residual Utility for Primary-Preserving Cognitive Decision Correction in Automatic Modulation Classification [1.547549252134621]
  We study a post-inference problem through cross-fitted residual utility and a primary-preserving cognitive decision policy.<n>A structured KAN-Fourier classifier supplies the default probability, while neural and non-neural candidates provide observable evidence.<n>On RMLA, RMLB, and HISAR, the complete system improves overall accuracy from 63.632% to 66.332%, 65.161% to 66.168%, and 77.769% to 79.867%.
  arXiv  Detail & Related papers  (2026-08-03T11:07:37Z)
• ALIVE: Warnings Before Exclusion in Budgeted Multi-Source Learning [18.17400877167872]
  A routing decision can be revised at the next transaction, but a latched source exclusion persists across later decisions.<n>We ask what evidence should authorize unequal-persistence actions when finite-population auditing and learning share a budget.
  arXiv  Detail & Related papers  (2026-07-31T13:18:47Z)
• What Accuracy and Gradient Cosine Miss: Evaluating Feedback Alignment via Scale Stability, Reference Validity, and Depth Utility [48.10132234701036]
  We propose a diagnostic evaluation protocol based on three checks -- scale stability, reference validity, and depth utility -- together with per-layer rather than aggregate cosine reporting.<n>Across multiple architectures and methods, our protocol identifies all failures with wide calibration margins.
  arXiv  Detail & Related papers  (2026-06-19T06:04:17Z)
• Hierarchical Certified Semantic Commitment for Byzantine-Resilient LLM-Agent Collaboration [30.310793549183117]
  We introduce Hierarchical Certified Semantic Commitment (H-CSC), a BFT-inspired protocol that converts embedding-derived finality signals over verdict-emitting proposal groups into one of three typed outcomes.<n>H-CSC commits with low angular deviation on BFT-feasible buckets (0.31 to 2.04 degrees) and aborts 100% of beyond-BFT rounds (n3f+1) as intended.
  arXiv  Detail & Related papers  (2026-06-05T14:35:58Z)
• Evidence-Grounded Ensemble Diagnosis of 802.11 Packet Captures: A Multi-Stage Pipeline with Deterministic Reliability Scoring [1.0170129555792935]
  Diagnosing 802.11 packet captures requires expert protocol knowledge, is slow, inconsistent across engineers, and unscalable.<n>LLM-based approaches sound plausible but fabricate protocol events absent from captures, produce uncalibrated confidence scores, and suffer evaluation bias when golden references are co-produced by the model under test.<n>We introduce PROBE, a multi-stage pipeline addressing all three failures.
  arXiv  Detail & Related papers  (2026-06-05T03:39:58Z)
• Refute-or-Promote: An Adversarial Stage-Gated Multi-Agent Review Methodology for High-Precision LLM-Assisted Defect Discovery [0.685316573653194]
  Refute-or-Promote is an inference-time reliability pattern combining Stratified Context Hunting (SCH) for candidate generation, adversarial kill mandates, context, and a Cross-Model Critic (CMC)<n>We present Refute-or-Promote, an inference-time reliability pattern combining Stratified Context Hunting (SCH) for candidate generation, adversarial kill mandates, context, and a Cross-Model Critic (CMC)<n>We present Refute-or-Promote, an inference-time reliability pattern combining Stratified Context Hunting (SCH) for candidate generation, adversarial kill mandates, context, and a Cross-Model Critic (CMC)
  arXiv  Detail & Related papers  (2026-04-21T03:55:35Z)
• FACT-E: Causality-Inspired Evaluation for Trustworthy Chain-of-Thought Reasoning [49.65751420291115]
  Chain-of-Thought (CoT) prompting has improved LLM reasoning, but models often generate explanations that appear coherent while containing unfaithful intermediate steps.<n>We propose FACT-E, a causality-inspired framework for evaluating CoT quality.<n>We show that FACT-E improves reasoning-trajectory selection and yields stronger in-context learnings.
  arXiv  Detail & Related papers  (2026-04-12T15:35:08Z)
• Cross-Context Verification: Hierarchical Detection of Benchmark Contamination through Session-Isolated Analysis [0.0]
  Cross-Context Verification (CCV) is a black-box method that solves the same benchmark problem in N independent sessions.<n>On 9 SWE-bench Verified problems (45 trials, Claude Opus 4.6, temperature 0), CCV achieves perfect separation between contaminated and genuine reasoning.
  arXiv  Detail & Related papers  (2026-03-23T00:18:34Z)
• From Black Box to Glass Box: Cross-Model ASR Disagreement to Prioto Review in Ambient AI Scribe Documentation [43.148402136307716]
  Cross-model disagreement among heterogeneous ASR systems can act as a reference-free uncertainty signal.<n>We transcribed 50 publicly available medical audio clips with eight ASR systems spanning commercial APIs and open-source engines.<n>Low-agreement regions were enriched for content disagreements, with the content fraction increasing from 53.9% to 73.9% across quintiles of high-risk mass.
  arXiv  Detail & Related papers  (2026-03-02T13:02:13Z)
• CIRCUS: Circuit Consensus under Uncertainty via Stability Ensembles [1.3011345529764784]
  We show that CIRCUS produces a threshold-robust "core" circuit while explicitly surfacing contingent alternatives.<n>On Gemma-2-2B and Llama-3.2-1B, strict consensus circuits are 40x smaller than the union of constructs all configurations while retaining comparable influence-flow explanatory power.<n>We further validate causal relevance with activation patching, where consensus-identified nodes consistently beat matched non-consensus controls.
  arXiv  Detail & Related papers  (2026-02-28T07:44:04Z)
• 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)
• Unsupervised Conformal Inference: Bootstrapping and Alignment to Control LLM Uncertainty [49.19257648205146]
  We propose an unsupervised conformal inference framework for generation.<n>Our gates achieve close-to-nominal coverage and provide tighter, more stable thresholds than split UCP.<n>The result is a label-free, API-compatible gate for test-time filtering.
  arXiv  Detail & Related papers  (2025-09-26T23:40:47Z)
• TrustJudge: Inconsistencies of LLM-as-a-Judge and How to Alleviate Them [58.04324690859212]
  Large Language Models (LLMs) as automated evaluators (LLM-as-a-judge) has revealed critical inconsistencies in current evaluation frameworks.<n>We identify two fundamental types of inconsistencies: Score-Comparison Inconsistency and Pairwise Transitivity Inconsistency.<n>We propose TrustJudge, a probabilistic framework that addresses these limitations through two key innovations.
  arXiv  Detail & Related papers  (2025-09-25T13:04:29Z)

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.