Logical Connectives

Follow this topic Ask about this topic

Momentum

3 papers in the last four weeks, level with the four weeks before. 0.0% of all new papers.

Jul 13Week of Sep 28

Latest papers 35

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
Topological Signal Processing With Unoriented Operators
Sep 21, 2026Andrea Cavallo, Varun Sarathchandran, Geert Leus +1Graph Signal Processing Tensor Decomposition
Delft University of Technology, Delft, Netherlands
Toward a Unified Mathematics of Concepts
Sep 21, 2026Chen ShaniCognitive Science Logical Connectives
School of Industrial & Intelligent Systems Engineering Tel Aviv University Israel
MasterControl Seventeen Every Time
Sep 2, 2026MasterControl AI LabEnterprise Analytics Governed
MasterControl AI Lab
Dictionary-Guided Mutation Operators for Automated HDL Repair
Sep 1, 2026Maisha Mastora, Dean SullivanRepair High-Level Synthesis
Department of Electrical and Computer Engineering University of New Hampshire Durham, NH, USA
Beyond Surface Forms: Symbolic Edits as a Test for Logical Reasoning with LLMs
Aug 31, 2026Ramya Keerthy Thatikonda, Wray Buntine, Ehsan ShareghiLLM Reasoning Strategies Reasoning Skills
Department of Data Science & AI, Monash University · ∃Department of Computer Science, University College London
KV-Skill: Forging Expertise in the Model's Native Language
Aug 5, 2026Zhaowei Han, Xiang Zhang, Bing Han +3Qwen3 Frozen Language Model
University of Michigan, Ann Arbor, MI, USA
Stochastic Sequential Search in Very-High-Dimensional Feature Selection
Aug 2, 2026Petr Somol, Jiří GrimFeature Selection High-Dimensional
Institute of Information Theory and Automation, The Czech Academy of Sciences Prague, Czech Republic
It's All Just Vectorization: einx, a Universal Notation for Tensor Operations
Jul 30, 2026Florian Fervers, Sebastian Bullinger, Christoph Bodensteiner +1Vectorization Tensor Networks
Fraunhofer IOSB
Expanding Flow Maps
Jul 23, 2026Sophia Tang, Pranam ChatterjeeGenerative Flow Networks Flow Map
Department of Computer and Information Science, University of Pennsylvania · Department of Bioengineering, University of Pennsylvania
Training, Reading, and Editing Legible Transformers
Jul 9, 2026Mark OskinTransformer Architectures Model Activations
School of Computer Science and Engineering University of Washington
Self-explainable Operator Learning for Discovering Spatial Patterns in Functional Data
Jul 2, 2026Mojgan Alishiri, Amirhossein ArzaniProbabilistic Operator Learning Logical Connectives
1Scientific Computing and Imaging Institute, University of Utah, Salt Lake City, UT, 84112, United States · 2Mechanical Engineering Department, University of Utah, Salt Lake City, UT, 84112, United States
GRPO, Dr. GRPO, and DAPO Are Three Operations on One Number: The Group-Standard-Deviation Identity
Jun 30, 2026Yong Yi Bay, Kathleen A. YearickVariance Disagreement
PhD, University of Illinois at Urbana-Champaign
TACO: Tool-Augmented Credit Optimization for Agentic Tool Use
Jun 29, 2026Mingkuan Feng, Jinyang Wu, Hao Gu +5Multimodal Agents Agentic
Department of Automation, BNRist, Tsinghua University · Institute of Automation, Chinese Academy of Sciences
Statistically Indistinguishable, Operationally Distinct: A Formal Barrier for Tabular Foundation Models
Jun 27, 2026Tassilo Klein, Johannes HoffartTabular Foundation Models Counter Turing Test
SAP SE
SemPiper: Interactive Code Synthesis for Semantic Operators in Machine Learning Pipelines
Jun 12, 2026Olga Ovcharenko, Luciano Duarte, Sebastian SchelterLarge Language Model Pipelines Llm-Driven Code Synthesis
BIFOLD & TU Berlin
Harness In-Context Operator Learning with Chain of Operators
Jun 10, 2026Minghui Yang, Ling Guo, Liu YangLogical Connectives In-Context Learning
Department of Mathematics, Shanghai Normal University, Shanghai, China · Department of Mathematics, National University of Singapore, Singapore
AbstRAG: Learning to Abstract for Retrieval Problems
Jun 8, 2026Lei Xu, Xin Quan, Daniel Pedronette +1Question-Answering Benchmarks Evidence Conflict
Idiap Research Institute, Switzerland · São Paulo State University, Brazil · Department of Computer Science, University of Manchester, United Kingdom +1
DiffSpot: Can VLMs Spot Fine-Grained Visual Differences in Web Interfaces?
May 28, 2026Linhao Zhang, Aiwei Liu, Yuan Liu +1Image-Text Alignment Logical Connectives
WeChat AI, Tencent Inc.
ReasonOps: Operator Segmentation for LLM Reasoning Traces
May 28, 2026Daniel Lee, Owen Queen, James ZouReasoning Traces LLM Reasoning Strategies
Stanford University
Learning High-Dimensional Parity Functions with Product Networks using Gradient Descent
May 27, 2026Guillaume Larue, Louis-Adrien Dufrène, Quentin Lampin +2Two-Layer Neural Networks High-Dimensional
Orange Research, Meylan, France · Télécom Paris, Institut Polytechnique de Paris, Palaiseau, France · Télécom Paris, Institut Polytechnique de Paris, Palaiseau, France.
An Enhanced Large Neighborhood Search Approach for the Capacitated Facility Location Problem with Incompatible Customers
May 27, 2026Ida Gjergji, Lucas Kletzander, Nysret Musliu +1Vehicle Routing Problem Large Neighborhood Search
DBAI, TU Wien, Austria · University of Udine, Italy
Learning Logical Operations for Arbitrary Quantum Error Correction Codes
May 27, 2026Nico Meyer, Christopher Mutschler, Dominik Seuß +2Quantum Error Correction Quantum Processor
Fraunhofer IIS, Fraunhofer Institute for Integrated Circuits IIS, Nuremberg, Germany · Pattern Recognition Lab, Friedrich-Alexander-University Erlangen-Nuremberg, Erlangen, Germany · University of Technology Nuremberg (UTN), Nuremberg, Germany +1
An Operator-Based Approach to STL
May 27, 2026Panagiotis Rousseas, Dimos V. DimarogonasSignal Temporal Logic Reachability
Department of Decision and Control Systems, School of Electrical Engineering and Computer Science, Royal Institute of Technology KTH, Sweden.
Physical Simulators as Do-Operators: Causal Discovery under Latent Confounders for AI-for-Science
May 8, 2026Tsuyoshi OkitaCausal Discovery Methods Latent Confounders
Kyushu Institute of Technology
ANDRE: An Attention-based Neuro-symbolic Differentiable Rule Extractor for Inductive Logic Programming
May 5, 2026Iman Sharifi, Peng Wei, Saber FallahNeuro-Symbolic Framework Induction
Dept. of Mechanical and Aerospace Engineering, George Washington University, USA · Dept. of Mechanical Engineering Sciences, University of Surrey, UK
Redefining AI Red Teaming in the Agentic Era: From Weeks to Hours
May 5, 2026Raja Sekhar Rao Dheekonda, Will Pearce, Nick LandersRed-Teaming Open-Source
1Dreadnode, USA
An explicit operator explains end-to-end computation in the modern neural networks used for sequence and language modeling
Apr 22, 2026Anif N. Shikder, Ramit Dey, Sayantan Auddy +6State Space Models Sequence Modeling
Department of Mathematics, Western University, London ON, Canada · Fields Lab for Network Computation, Fields Institute, Toronto ON, Canada · King’s University College at Western University, London ON, Canada +1
Where Reasoning Breaks: Logic-Aware Path Selection by Controlling Logical Connectives in LLMs Reasoning Chains
Apr 22, 2026Seunghyun Park, Yuanyuan LeiReasoning Chain Reasoning Skills
Independent Researcher · University of Florida Gainesville, FL, United States
Decompose, Structure, and Repair: A Neuro-Symbolic Framework for Autoformalization via Operator Trees
Apr 21, 2026Xiaoyang Liu, Zineng Dong, Yifan Bai +3Autoformalization Neuro-Symbolic Framework
School of Mathematical Sciences, Shanghai Jiao Tong University · Zhiyuan College, Shanghai Jiao Tong University · Institute of Natural Sciences, MOE-LSC, CMA-Shanghai, Shanghai Jiao Tong University
Evolutionary design of thermodynamic logic gates and their heat emission
Feb 13, 2026Stephen WhitelamThermodynamics Genetic Algorithms
Molecular Foundry, Lawrence Berkeley National Laboratory, 1 Cyclotron Road, Berkeley, CA 94720, USA
Beyond Dense States: Sparse Transcoders as Causally Testable Operators for LLM Latent Reasoning
Feb 2, 2026Yadong Wang, Haodong Chen, Yu Tian +3Efficient Latent Reasoning Logical Connectives
Nanjing University of Aeronautics and Astronautics · State Key Laboratory of Ocean Sensing, ZJU-Hangzhou Global Scientific and Technological Innovation Center, Zhejiang University, Hangzhou, 311215, China · Security Capability Center
A Quantitative Study of Sustained Focus in Large Language Models via Repetitive Deterministic Prediction Tasks
Nov 2, 2025Wanda Hou, Leon Zhou, Hong-Ye Hu +3Logical Connectives
EdenCode Inc. · Stevenson School · Harvard University +2
A Concept of Possibility for Real-World Events
Oct 3, 2025Daniel G. SchwartzPossibilities Logical Connectives
Florida State University, USA
Discrete Compositional Generation via General Soft Operators and Robust Reinforcement Learning
Jun 20, 2025Marco Jiralerspong, Esther Derman, Danilo Vucetic +5Kullback-Leibler Regularization Rejection Sampling
1Université de Montréal · 2Mila · 5Independent +1

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 35