Equivalence

Follow this topic Ask about this topic

Momentum

7 papers in the last four weeks, up 17% on the four weeks before. 0.1% of all new papers.

Jul 13Week of Sep 28

Latest papers 73

All topics

Semantic Uncertainty Quantification Needs Factual Equivalence
Sep 28, 2026Joseph Hoche, Quentin Guimard, Gianni FranchiLarge Language Model Uncertainty Uncertainty
AMIAD, Pˆole Recherche Palaiseau, France
The Linear Representation Hypothesis Needs a Group Action
Sep 22, 2026Louie Hong Yao, Yuhao Li, Shengchao LiuRepresentation Space Interpretability
The Chinese University of Hong Kong
The Output-Space Hypothesis: Enumerative Equivalence Checking for Tensor Programs
Sep 17, 2026Paul Biberstein, Joseph Devietti, Mayur NaikCuda Bug
University of Pennsylvania Philadelphia, PA, USA
Recurrent GraphNeural NetworkswithSet-BasedAggregation
Sep 14, 2026Blai BonetReachability Neural Network Verification
Universidad Simón Bolívar Caracas, Venezuela
Groupoid-Based Internal State Representations for Reinforcement Learning with Local Symmetries
Sep 14, 2026Ben Opperman, Eduardo Alonso, Esther MondragónGroup-Based Reinforcement Learning Symmetry
CitAI, AI Research Centre, City St George’s, University of London, London, United Kingdom
Interpolation Is Not Invariance: Pair Count Is Not Coverage in Transformation Audits
Sep 14, 2026Mohammed Ahnouch, Lotfi ElaachakModel Auditing Long-Run Coverage Guarantees
Université Paris 1 Paris, France · Faculty of Science and Technology of Tangier Abdelmalek Essaadi University Tangier, Morocco
Settling: Equilibrium Inference for Non-Convex Validity Sets
Sep 9, 2026Lyes Saad SaoudUncoupled Learning Self-Consistency
Independent Researcher, Chicago, IL, USA.
From Base Rollouts to RL Reasoning: A Budgeted Search Perspective
Sep 1, 2026Wenhe Sun, Cunxiang Wang, Zijun Yao +1Offline Reinforcement Learning Parallel Rollouts
1Fudan University · 2Zhipu AI · 3Tsinghua University +1
REFACTOR-VLA: Unsupervised Library Learning of Typed Motor Programs
Sep 1, 2026Riyaaz Shaik, Chandru VenkataramanMotion Control Equivalence
Apple
A Certificate-Producing Cascade for Equational Implication: The SAIR EQT2 Stage 2 Solver
Sep 1, 2026Haobo Ma, Wenlin Zhang, Manuel Israel CázaresEquivalence Theorem Proving
ChronoAI Pte. Ltd. · Singapore · National University of Singapore +2
Persistent Magnitude Homology for Quantitative Equational Theories
Aug 21, 2026Luciano MelodiaPersistent Homology Equivalence
Friedrich-Alexander Universität Erlangen-Nürnberg, Germany
Process-Constituted Intelligence: A Shared Criterion for Humans and Machines
Aug 17, 2026Michael J. Richardson, Ayeh Alhasan, Cassandra Crone +5Generative Artificial Intelligence Generative Processes
School of Psychological Sciences, Macquarie University, Sydney, NSW 2109, Australia · Performance and Expertise Research Centre, Macquarie University · Frontier AI Research Centre, Macquarie University +3
PAC-Bayes Beyond Parameter Space: Behavioral Equivalence, Z-Information, and Exact Complexity Decomposition
Aug 11, 2026Vasant G. Honavar, Satish Kumar Keshri, Neil Ashtekar +1Pac-Bayesian Theory Kullback-Leibler Divergence
Artificial Intelligence Research Laboratory Department of Informatics and Intelligent Systems The Pennsylvania State University · Artificial Intelligence Research Laboratory Department of Computer Science and Engineering The Pennsylvania State University
No Unique Minimizer, No Problem: On the Consistency of Robust Neural Classifiers
Aug 9, 2026Subhabrata Majumdar, Anand Deo, Partha Pratim Saha +1Empirical Risk Minimization Cross-Entropy Losses
Indian Institute of Management Bangalore · Independent Researcher · Indian Statistical Institute, Kolkata
Surrogate Substitution Preserves PHI Detectability: A Multi-Detector Equivalence Study
Aug 4, 2026Qiming Bao, Sherry J. H. Feng, Kim Chester Eugenio +1De-Identification Substitute
Custodian Labs
Hypercubes, Hyperplanes, and Constraint-Induced Complexity Collapse in Atomic Concept Learning
Aug 3, 2026Irene TsaparaHypothesis Class Atoms
National University, San Diego, United States
ModelEquivBench: Certifying Multi-Relational Evaluation of LLM-Generated Optimization Models
Jul 31, 2026Penglin Zhu, Jungang XuOptimization Modeling Equivalence
School of Computer Science and Technology, University of the Chinese Academy of Sciences
AgentMap: Joint Equivalence and Subsumption Discovery for Ontology Matching
Jul 29, 2026Yiping Song, Jiaoyan Chen, Renate Schmidt +2Ontology Semantic Relationships
Department of Computer Science, The University of Manchester, UK · School of Software Technology, Zhejiang University, China
Equality, Equity, and Causality in Fairness Research: A Commentary on Cheng (2026)
Jul 20, 2026Youmi SukAlgorithmic Fairness Psychometric Properties
Teachers College, Columbia University
Controlled Reformulation Testing for Logical Consistency in Large Language Models
Jul 16, 2026Alexander Gu, Alan ChenReasoning Skills Rewrite
University of Texas at Austin
When Close Enough Is Not Enough: Autoregressive Drift in Quantum Circuit Synthesis
Jul 14, 2026Mehdi Saeedi, Eddie Richter, Paul HartkeQuantum Circuits Autoregressive Model
Advanced Micro Devices, Inc. (AMD)
The Equilibrium Is the Initialization: Lazy Identity Collapse in Physics-Structured Deep Equilibrium Reasoning
Jul 13, 2026Joyjeet SinghEquilibrium Equivalence
Independent Researcher
The Illusion of Equivalency: Statistical Characterization of Quantization Effects in LLMs
Jul 9, 2026Baha Rababah, Cuneyt Gurcan Akcora, Carson K. LeungLarge Language Model Quantization Post-Training Quantization
Department of Computer Science, University of Manitoba, Canada · AI Initiative, University of Central Florida, USA
The Rank-One Corner: How Much Value Equivalence Does a Task Need from a World Model?
Jul 7, 2026Donna VakalisWorld Models Equivalence
Mila – Quebec AI Institute Université de Montréal Montréal, Québec
Learning Sparsest Linear Causal DAGs with Latent Confounders via Higher-Order Cumulants
Jul 7, 2026Ming Cai, Hisayuki HaraDirected Acyclic Graph Latent Confounders
Graduate School of Informatics, Kyoto University, Kyoto, Japan · Institute for Liberal Arts and Sciences, Kyoto University, Kyoto, Japan
Teacher Supervision over Representation Equivalence Classes
Jul 3, 2026Sang Il HanTeacher Equivalence
Korea University of Technology and Education · Biomonster Co.
The Signal-Coverage Matrix: Stratifying Type and Semantic Errors in Statement Autoformalization
Jun 26, 2026Chengxiao Dai, Zhaokun Yan, Zhanhui LinAutoformalization Formalization
School of Computer Science, University of Sydney, Sydney, Australia · China Academy of Information and Communications Technology, China
Theory-Scale Auto-Formalization of Logics for Computer Science
Jun 25, 2026Yuming Feng, Frederick Pu, One An +5Autoformalization Formal Verification
Johns Hopkins University · University of Toronto · University of Pennsylvania +1
Beyond Shapley: Efficient Computation of Asymmetric Shapley Values
Jun 23, 2026Ezequiel Companeetz, Santiago Cifuentes, Sergio AbriolaShapley Value Equivalence
Departamento de Computación, Facultad de Ciencias Exactas y Naturales, UBA · Instituto de Ciencias de la Computación (ICC), CONICET
Does My Embedding Reflect That $A = B$ ? Evaluating Mathematical Equivalence in Embedding Models
Jun 22, 2026Jiaying Ye, Samarth Rao, Leo Carlin +9Formalization Equivalence
University of Washington · Axiom Math, University of Washington · Pacific Northwest National Laboratory
The Faithfulness Gap: Certifying Semantic Equivalence Between Natural-Language and Formal Mathematical Statements
Jun 15, 2026Noor Islam S. Mohammad, Tamim SheikhAutoformalization Formalization
Department of Computer Science, Informatics Institute, Istanbul Technical University, Istanbul, Türkiye · Department of Computer Science and Engineering, Jashore University of Science and Technology, Bangladesh.
LAUKIN: A Multi-jurisdictional Common Law Contract Dataset
Jun 11, 2026Amrita Singh, Aditya Joshi, Jiaojiao Jiang +2Legal Domain Natural Language Processing
Computer Science and Engineering, UNSW, Sydney, Australia · Law and Justice, UNSW, Sydney, Australia
On the conditional equivalence of phase retrieval algorithms
Jun 5, 2026Jakob Schroeder, Andreas DöppImage Reconstruction Differentiable Physics
Fakultät für Physik, Ludwig-Maximilian-Universität München, Am Coulombwall 1, 85748 Garching, Germany · Munich Center for Machine Learning (MCML) · Max Planck Institut für Quantenoptik, Hans-Kopfermann-Strasse 1, Garching 85748, Germany
Harnessing Structural Context for Entity Alignment Foundation Models
Jun 4, 2026Xingyu Chen, Yuanning Cui, Zequn Sun +1Hierarchical Semantic Alignment Cross-Encoder
State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China · Nanjing University of Information Science and Technology, Nanjing, China · National Institute of Healthcare Data Science, Nanjing University, Nanjing, China
Beyond Objective Equivalence: Constraint Injection for LLM-Based Optimization Modeling on Vehicle Routing Problems
Jun 3, 2026Xizi Luo, Changhong He, Dongdong Geng +2Optimization Modeling Vehicle Routing Problem
Beihang University, Beijing, China · Baidu Inc., Beijing, China
Exact equivariance, kept through training, buys zero-shot generalisation across the symmetry group
Jun 2, 2026Hongbo WangRotation Equivariance Equivariance
Department of Mathematics, Stony Brook University, Stony Brook, NY 11794, USA
Measuring the Symmetry--Data Exchange Rate
May 31, 2026Ahmed M. AdlyEquivariance Equivalence
Independent Researcher · Egypt
Universal Decision Learners
May 29, 2026Sridhar MahadevanDecisions Equivalence
Adobe Research San Jose, CA · Academic affiliation: Research Professor, University of Massachusetts, Amherst
Converted, Not Equivalent: Benchmarking Codebase Conversion via Observational Equivalence
May 27, 2026Linxin Song, Jiefeng Chen, Yue Huang +5Codebases Pass-Rate Evaluation
University of Southern California · Google Cloud AI Research · University of Notre Dame +1
FormInv: A Measurement Protocol for Semantic Invariance in Mathematical Reasoning Benchmarks
May 27, 2026Nishal Thomas, Noel ThomasMathematical Reasoning Benchmarks Theorem Proving
Independent Researcher · Mohamed Bin Zayed University of Artificial Intelligence
Human-in-the-Loop Contextual Bandits for Short-Term Rental Dynamic Pricing: Structural Equivalence of Historical Warm-Up and Approval-Gated Live Learning
May 22, 2026Oleg MiroshnichenkoDynamic Pricing Contextual Bandit Framework
Entropy Equivalence Testing
May 22, 2026Clément L. Canonne, Yash Pote, Jonathan Scarlett +1Two-Sample Testing Optimal Sample Complexity
University of Sydney · National University of Singapore
What are the Right Symmetries for Formal Theorem Proving?
May 21, 2026Krzysztof Olejniczak, Radoslav Dimitrov, Xingyue Huang +3Theorem Proving Equivalence
University of Oxford · KAIST · TU Wien +1
Causal Discovery in Structural VAR Models Under Equal Noise Variance
May 21, 2026SeyedSina Seyedi HasanAbadi, Fahimeh Arab, Erfan Nozari +1Multivariate Time-Series Equivalence
Bourns College of Engineering, University of California, Riverside · University of California, San Francisco · Department of Mathematics and Statistics, Boston University
Conditional Equivalence of DPO and RLHF: Implicit Assumption, Failure Modes, and Provable Alignment
May 20, 2026Zhiqin Yang, Yonggang Zhang, Wei Xue +3Backtranslation Augmented Direct Preference Optimization Reinforcement Learning From Human Feedback
1The Hong Kong University of Science and Technology · 2LIGHTSPEED · 3Hong Kong Baptist University.
Saturating Scaling Laws for Equational Discovery: A Phenomenology of Growth Dynamics in Three Toy Substrates with Two Real-World Replications
May 14, 2026Fabio RovaiScaling Laws Growth
Tesseract Academy
When Are Two Networks the Same? Tensor Similarity for Mechanistic Interpretability
May 14, 2026ML Nissen Gonzalez, Melwina Albuquerque, Laurence Wroe +3Mechanistic Interpretability Tensor Networks
MARS & University Heidelberg · MARS · MARS & Stanford University +2
On Strong Equivalence Notions in Logic Programming and Abstract Argumentation
May 14, 2026Giovanni Buraglio, Wolfgang Dvorak, Stefan WoltranLogic Equivalence
TU Wien, Austria
Reward-Weighted On-Policy Distillation with an Open Property-Equivalence Verifier for NL-to-SVA Generation
May 13, 2026Qingyun Zou, Yingze Li, Tianen Liu +2Systemverilog Assertions High-Level Synthesis
National University of Singapore
Coarsening Linear Non-Gaussian Causal Models with Cycles
May 11, 2026Francisco Madaleno, Francisco C Pereira, Alex MarkhamCausal Modeling Causal Representation Learning
Department of Technology, Management and Economics, Technical University of Denmark · Department of Mathematical Sciences,11 University of Copenhagen
The Gordian Knot for VLMs: Diagrammatic Knot Reasoning as a Hard Benchmark
May 11, 2026Hao Liu, Jicheng LiuVisual Reasoning Diagrams
Department of Psychology New York University · Department of Computer Science University of Southern California
Equivalence of Coarse and Fine-Grained Models for Learning with Distribution Shift
May 7, 2026Adam R. Klivans, Shyamal Patel, Konstantinos Stavropoulos +1Learnability Distribution Shifts
UT Austin · Columbia University
How Well Do LLMs Perform on the Simplest Long-Chain Reasoning Tasks: An Empirical Study on the Equivalence Class Problem
May 7, 2026Chun Zheng, Lianlong Wu, Bingqian Li +2LLM Reasoning Strategies Large Reasoning Models
University of Science and Technology of China · University of Oxford
Practical validation of synthetic pre-crash scenarios
May 6, 2026Jian Wu, Ulrich Sander, Carol Flannagan +1Two-Sample Testing Validation
Safety Center, Volvo Cars, 41878 Göteborg, Sweden · Department of Mechanics and Maritime Sciences, Chalmers University of Technology, 41756 Göteborg, Sweden · University of Michigan Transportation Research Institute, Ann Arbor, Michigan 48109, USA
Structural Equivalence and Learning Dynamics in Delayed MARL
May 5, 2026Jules Sintes, Ana Bušić, Jiamin ZhuPartially Observable Markov Decision Process Multi-Agent Reinforcement Learning
Inria · DIENS, École Normale Supérieure, PSL University · Paris, France +2
On the Spectral Structure and Objective Equivalence of Orthogonal Multilabel Fisher Discriminants
May 5, 2026Brian Keith-Norambuena, Juan Bekios-CalfaMulti-Label Classification Discriminative Models
Department of Computing & Systems Engineering, Universidad Cat´olica del Norte, Antofagasta, Chile.
Learning Correct Behavior from Examples: Validating Sequential Execution in Autonomous Agents
May 4, 2026Reshabh K Sharma, Gaurav Mittal, Yu HuAutonomous Agents Probabilistic Model Checking
University of Washington, Seattle, WA, USA · Microsoft, Redmond, WA, USA
Less Is More: Cognitive Load and the Single-Prompt Ceiling in LLM Mathematical Reasoning
Apr 20, 2026Manuel Israel CazaresMathematical Reasoning LLM Reasoning Strategies
Bytepro AI Mazatlán, Sinaloa, Mexico
From Legal Text to Executable Decision Models: Evaluating Structured Representations for Legal Decision Model Generation
Apr 18, 2026David GrausLegal Reasoning Tasks Large Language Model Decisions
University of Amsterdam · Amsterdam, The Netherlands
Improving LLM Code Reasoning via Semantic Equivalence Self-Play with Formal Verification
Apr 18, 2026Antonio Valerio Miceli Barone, Poon Tsz NokEquivalence Llm-Driven Code Synthesis
School of Informatics, University of Edinburgh

Sep 28, 2026, cs.CLJ/K move · Enter open · S save

Semantic Uncertainty Quantification Needs Factual Equivalence

Joseph Hoche, Quentin Guimard, Gianni Franchi

AMIAD, Pˆole Recherche Palaiseau, France

Large Language Model Uncertainty Uncertainty Equivalence Token-Level Uncertainty Logical Connectives Encoders

Open paper AskPDF arXiv

Semantic uncertainty quantification for large language models rests on a common template: sample several answers, measure how much they agree, and treat disagreement as uncertainty. We first formalize this template as two separate roles: an operator that compares two answers, and an aggregator that combines all pairwise comparisons into a scalar. Existing methods differ almost entirely in how they aggregate, while taking the operator off the shelf, typically an NLI model or a generic sentence encoder. We show that this reliance on off-the-shelf operators is the primary bottleneck of semantic UQ: they do not accurately measure factual equivalence of multiple answers to the same question. We resolve this with a deliberately simple recipe: a single encoder trained contrastively to isolate the targeted fact, utilizing synthetic data generated by an LLM and dataset both disjoint from all evaluation settings. Integrating the resulting operator into existing methods improves performance on 120 of 126 evaluation settings (95%) spanning 18 model dataset combinations across language and vision-language models. The best variant reaches 0.76 mean AUROC against 0.68 for the strongest baseline, while replacing the quadratic cross-encoder comparisons of entailment-based operators with one encoder pass per answer. The uniformity of the improvement supports the view that the operator, not the aggregator, is the limiting factor. The same operator also improves single generation token-level estimators: the norm it assigns to each token measures how much that token bears on the answer, and reweighting token log-likelihoods accordingly sharpens the estimate.

Momentum

Related topics

Latest papers 73