Related papers: Credibility-Limited Revision for Epistemic Spaces

Related papers

ActReview: Rebuttal-Guided Training Data and Rubric Rewards for Actionable Peer Review Generation [54.82704239643649]
We introduce ActReview, a rebuttal-guided post-training framework that connects paper-specific diagnoses to concrete, grounded revision plans.<n>Our central insight is that author rebuttals reveal plausible actions for addressing reviewer concerns and can therefore provide latent supervision for revision-oriented feedback.<n>We also introduce ActReview-Bench, a human-curated benchmark of 1,000 instances for evaluating diagnostic quality and revision usefulness.
arXiv Detail & Related papers (2026-09-08T17:30:16Z)
COSMO: Consensus-Driven Shift Modulation for Source-Free Domain Adaptation [79.43842208099619]
Source-free domain adaptation (SFDA) adapts a source-trained model to an unlabeled target domain without source data.<n>We formulate VLM-guided SFDA as a sample-wise reliability-allocation problem.<n>We propose Consensus-Driven Shift Modulation (COSMO) to replace expert-to-expert guidance with co-adaptation.
arXiv Detail & Related papers (2026-08-05T09:10:30Z)
Selective Credibility-Limited Belief Update [0.0]
We introduce selective credibility-limited belief update.<n>We provide semantic and axiomatic characterizations of the resulting class of update operators.<n>These results demonstrate that the framework provides a unified and strictly more expressive account of belief update.
arXiv Detail & Related papers (2026-07-30T17:00:38Z)
IMPACT-CYCLE: A Contract-Based Multi-Agent System for Claim-Level Supervisory Correction of Long-Video Semantic Memory [73.22944697933603]
Existing pipelines produce opaque, end-to-end outputs that expose no intermediate state for inspection.<n>We present IMPACT-Cycle, a supervisory multi-agent system that reformulates long-video understanding as a multimodal iterative claim-level maintenance.
arXiv Detail & Related papers (2026-04-22T03:03:33Z)
Taming Actor-Observer Asymmetry in Agents via Dialectical Alignment [59.536125286960186]
Multi-agent frameworks assigning specialized roles are increasingly adopted to enable self-reflection and mutual auditing.<n>We find it simultaneously induces a human-like cognitive bias known as Actor-Observer Asymmetry.<n>ReTAS guides agents to synthesize conflicting viewpoints into an objective consensus.
arXiv Detail & Related papers (2026-04-21T15:05:58Z)
VI-CuRL: Stabilizing Verifier-Independent RL Reasoning via Confidence-Guided Variance Reduction [55.04308051033549]
Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as a dominant paradigm for enhancing Large Language Models (LLMs) reasoning.<n>We introduceVerifier-Independent Curriculum Reinforcement Learning (VI-CuRL), a framework that leverages the model's intrinsic confidence to construct a curriculum independent from external verifiers.
arXiv Detail & Related papers (2026-02-13T03:40:52Z)
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)
Illusions of Confidence? Diagnosing LLM Truthfulness via Neighborhood Consistency [78.91846841708586]
We show that even facts answered with perfect self-consistency can rapidly collapse under mild contextual interference.<n>We propose Neighbor-Consistency Belief (NCB), a structural measure of belief that evaluates response coherence across a conceptual neighborhood.<n>We also present Structure-Aware Training (SAT), which optimize context-invariant belief structure and reduces long-tail knowledge brittleness by approximately 30%.
arXiv Detail & Related papers (2026-01-09T16:23:21Z)
Commitment Checklist: Auditing Author Commitments in Peer Review [55.67642089544162]
We present a large-scale audit of author commitments using large language models (LLMs) to compare rebuttals against camera-ready versions.<n>We find that while a majority of promised changes are implemented, a significant share (about 25%) are not, with "missing experiments" among the most frequently unfulfilled.<n>We propose the idea of Author Commitment Checklist, which would alert authors and organizers to unaddressed promises.
arXiv Detail & Related papers (2026-01-08T05:37:09Z)
Automatic Reviewers Fail to Detect Faulty Reasoning in Research Papers: A New Counterfactual Evaluation Framework [55.078301794183496]
We focus on a core reviewing skill that underpins high-quality peer review: detecting faulty research logic.<n>This involves evaluating the internal consistency between a paper's results, interpretations, and claims.<n>We present a fully automated counterfactual evaluation framework that isolates and tests this skill under controlled conditions.
arXiv Detail & Related papers (2025-08-29T08:48:00Z)
Confidential Guardian: Cryptographically Prohibiting the Abuse of Model Abstention [65.47632669243657]
A dishonest institution can exploit mechanisms to discriminate or unjustly deny services under the guise of uncertainty.<n>We demonstrate the practicality of this threat by introducing an uncertainty-inducing attack called Mirage.<n>We propose Confidential Guardian, a framework that analyzes calibration metrics on a reference dataset to detect artificially suppressed confidence.
arXiv Detail & Related papers (2025-05-29T19:47:50Z)
Aurora: Are Android Malware Classifiers Reliable and Stable under Distribution Shift? [51.12297424766236]
AURORA is a framework to evaluate malware classifiers based on their confidence quality and operational resilience.<n>AURORA is complemented by a set of metrics designed to go beyond point-in-time performance.<n>The fragility in SOTA frameworks across datasets of varying drift suggests the need for a return to the whiteboard.
arXiv Detail & Related papers (2025-05-28T20:22:43Z)
On Definite Iterated Belief Revision with Belief Algebras [19.073043690553867]
We propose a novel framework for iterated belief revision by characterizing belief information through preference relations.<n>We prove that the revision result is uniquely determined given the current belief state and new evidence.<n>We argue that this approach may offer a more predictable and principled method for belief revision, making it suitable for real-world applications.
arXiv Detail & Related papers (2025-05-10T04:34:43Z)
AlignRAG: Leveraging Critique Learning for Evidence-Sensitive Retrieval-Augmented Reasoning [61.28113271728859]
RAG has become a widely adopted paradigm for enabling knowledge-grounded large language models (LLMs)<n>Standard RAG pipelines often fail to ensure that model reasoning remains consistent with the evidence retrieved, leading to factual inconsistencies or unsupported conclusions.<n>In this work, we reinterpret RAG as Retrieval-Augmented Reasoning and identify a central but underexplored problem: textitReasoning Misalignment.
arXiv Detail & Related papers (2025-04-21T04:56:47Z)
Is the Top Still Spinning? Evaluating Subjectivity in Narrative Understanding [50.94206345567363]
Forcing binary labels upon ambiguous claims lowers the reliability of evaluation. We introduce LLM-generated edits of summaries as a method of providing a nuanced evaluation of claims. We show that ARM produces a absolute 21% improvement in annotator agreement on claim faithfulness.
arXiv Detail & Related papers (2025-04-01T19:08:24Z)
Estimating Commonsense Plausibility through Semantic Shifts [66.06254418551737]
We propose ComPaSS, a novel discriminative framework that quantifies commonsense plausibility by measuring semantic shifts. Evaluations on two types of fine-grained commonsense plausibility estimation tasks show that ComPaSS consistently outperforms baselines.
arXiv Detail & Related papers (2025-02-19T06:31:06Z)
Calibrated Probabilistic Forecasts for Arbitrary Sequences [58.54729945445505]
Real-world data streams can change unpredictably due to distribution shifts, feedback loops and adversarial actors. We present a forecasting framework ensuring valid uncertainty estimates regardless of how data evolves.
arXiv Detail & Related papers (2024-09-27T21:46:42Z)
The Realizability of Revision and Contraction Operators in Epistemic Spaces [8.010966370223985]
AGM revision and AGM contraction operators are only realizable in precisely determined spaces. We define the class of linear change operators, a special kind of maxichoice operator. When AGM revision, respectively, AGM contraction, is realizable, linear change operators are a canonical realization.
arXiv Detail & Related papers (2024-07-30T15:55:01Z)
Certifiably Byzantine-Robust Federated Conformal Prediction [49.23374238798428]
We introduce a novel framework Rob-FCP, which executes robust federated conformal prediction effectively countering malicious clients. We empirically demonstrate the robustness of Rob-FCP against diverse proportions of malicious clients under a variety of Byzantine attacks.
arXiv Detail & Related papers (2024-06-04T04:43:30Z)
Diagnosing and Rectifying Fake OOD Invariance: A Restructured Causal Approach [51.012396632595554]
Invariant representation learning (IRL) encourages the prediction from invariant causal features to labels de-confounded from the environments. Recent theoretical results verified that some causal features recovered by IRLs merely pretend domain-invariantly in the training environments but fail in unseen domains. We develop an approach based on conditional mutual information with respect to RS-SCM, then rigorously rectify the spurious and fake invariant effects.
arXiv Detail & Related papers (2023-12-15T12:58:05Z)
System of Spheres-based Two Level Credibility-limited Revisions [0.0]
When revising by a two level credibility-limited revision, two levels of credibility and one level of incredibility are considered. We propose a construction for two level credibility-limited revision operators based on Grove's systems of spheres.
arXiv Detail & Related papers (2023-07-11T07:10:39Z)
Interpretable Automatic Fine-grained Inconsistency Detection in Text Summarization [56.94741578760294]
We propose the task of fine-grained inconsistency detection, the goal of which is to predict the fine-grained types of factual errors in a summary. Motivated by how humans inspect factual inconsistency in summaries, we propose an interpretable fine-grained inconsistency detection model, FineGrainFact.
arXiv Detail & Related papers (2023-05-23T22:11:47Z)
Hallucinated Adversarial Control for Conservative Offline Policy Evaluation [64.94009515033984]
We study the problem of conservative off-policy evaluation (COPE) where given an offline dataset of environment interactions, we seek to obtain a (tight) lower bound on a policy's performance. We introduce HAMBO, which builds on an uncertainty-aware learned model of the transition dynamics. We prove that the resulting COPE estimates are valid lower bounds, and, under regularity conditions, show their convergence to the true expected return.
arXiv Detail & Related papers (2023-03-02T08:57:35Z)
On Limited Non-Prioritised Belief Revision Operators with Dynamic Scope [2.7071541526963805]
We introduce the concept of dynamic-limited revision, which are revisions expressible by a total preorder over a limited set of worlds. For a belief change operator, we consider the scope, which consists of those beliefs which yield success of revision. We show that for each set satisfying single sentence closure and disjunction completeness there exists a dynamic-limited revision having the union of this set with the beliefs set as scope.
arXiv Detail & Related papers (2021-08-17T17:22:29Z)
On the use of evidence theory in belief base revision [0.0]
We propose the idea of credible belief base revision yielding to define two new formula-based revision operators. These operators stem from consistent subbases maximal with respect to credibility instead of set inclusion and cardinality.
arXiv Detail & Related papers (2020-09-24T12:45:32Z)
Mitigating Manipulation in Peer Review via Randomized Reviewer Assignments [96.114824979298]
Three important challenges in conference peer review are maliciously attempting to get assigned to certain papers and "torpedo reviewing" We present a framework that brings all these challenges under a common umbrella and present a (randomized) algorithm for reviewer assignment. Our algorithms can limit the chance that any malicious reviewer gets assigned to their desired paper to 50% while producing assignments with over 90% of the total optimal similarity.
arXiv Detail & Related papers (2020-06-29T23:55:53Z)
Belief Base Revision for Further Improvement of Unified Answer Set Programming [0.0]
The base revision operator is developed using Removed Set Revision strategy. The operator is characterized by respect to the postulates for base revisions operator satisfies.
arXiv Detail & Related papers (2020-02-27T08:31:01Z)

This list is automatically generated from the titles and abstracts of the papers in this site.