Epistemic Asymmetry

Follow this topic Ask about this topic

Momentum

0 papers in the last four weeks, against 1 the four weeks before. 0.0% of all new papers.

Jul 6Week of Sep 21

Latest papers 26

All topics

Explicit, Not Longer: What Makes Epistemic Stance Survive Memory Compression
Aug 7, 2026Alex KwonEpistemic Asymmetry Retention
Independent Researcher
Sycophancy Undermines Epistemic Vigilance in Cooperative Vision-Language Tasks
Jul 31, 2026Rupak Sarkar, Neha Srikanth, Saloni Gupta +3Epistemic Asymmetry Sycophancy
University of Maryland, College Park · Army Research Lab
Beyond Epistemia: Epistemic Schizologia and Large Language Models as Techno-Semiotic Machines
Jul 28, 2026Federico Cabitza, Gianluca ColomboEpistemic Asymmetry Linguistics
Department of Informatics, Systems and Communication, University of Milano-Bicocca, Milan, Italy · Digital Health and Wellbeing Center, Fondazione Bruno Kessler, Trento, Italy · Oneofftech-UG (haftungsbeschränkt), Berlin, Germany
Beyond Sally-Anne: Evaluating Theory of Mind in LLMs using Epistemic Schelling Points
Jul 13, 2026Roberta Rocca, Sami Boukortt, Geoff Keeling +1Theory-Of-Mind Reasoning Social Reasoning
1Google
Flout at Your Own Risk: LLMs Struggle with Pragmatic Cooperativity Under Epistemic Asymmetry
Jul 13, 2026Hannah VanderHoeven, Abhijnan Nath, Nikhil KrishnaswamyEpistemic Asymmetry Large Language Models Fail
Situated Grounding and Natural Language (SIGNAL) Lab Department of Computer Science Colorado State University Fort Collins, CO 80523, USA
Compaction as Epistemic Failure: How Agentic LLM Tools Fabricate Confirmed Results from Killed Processes
Jul 11, 2026Hiroki TambaLarge Language Models Fail Compaction
Independent Researcher
Study on Quantitative Dynamic Epistemic Logic for Belief Revision
Jun 18, 2026Felipe Nunes de Souza CamargoDynamic Epistemic Logic Logic
State University of Campinas (UNICAMP), Campinas-SP, Brasil
Co-Construction Blindness and Asymmetric Epistemic Vulnerability in Human-LLM Interaction
Jun 18, 2026Bianca Helena XimenesEpistemic Asymmetry Large Language Models Fail
Independent Researcher; Universidade Federal de Pernambuco (UFPE)
LLM Doesn't Know What It Doesn't Know: Detecting Epistemic Blind Spots via Cross-Model Attribution Divergence on Clinical Tabular Data
Jun 17, 2026Akshat Dasula, Prasanna Desikan, Jaideep SrivastavaLarge Language Model Reliability Epistemic Asymmetry
Centific AI Research · Department of Computer Science & Engineering, University of Minnesota-Twin Cities, Minneapolis, USA.
Exposure Bias as Epistemic Underidentification in Recursive Forecasting
Jun 11, 2026Riku Green, Zahraa S. Abdallah, Telmo M Silva FilhoNext-State Prediction Dynamic Epistemic Logic
University of Bristol, UK
Traxia: A Framework for Verifiable, Agent-Native Scientific Publishing
Jun 6, 2026Wisdom DogahJournal Peer Review
Faculty of Computing and Mathematical Sciences, University of Mines and Technology (UMaT), Tarkwa, Ghana. · BlackMatrix AI Research, Accra, Ghana.
Trust, but Don't Verify: Epistemic Blind Spots in LLM Source Evaluation
Jun 3, 2026Rohan N. Pradhan, Steve GoleyLarge Language Model Reliability Epistemic Asymmetry
Amazon
From Fact Overwriting to Knowledge Evolution: Causal Editing via On-Policy Self-Distillation
May 27, 2026Shuaike Li, Kai Zhang, Xianquan Wang +2Multimodal Knowledge Editing Epistemic Asymmetry
State Key Laboratory of Cognitive Intelligence, University of Science and Technology of China
Detecting Is Not Resolving: The Monitoring Control Gap in Retrieval Augmented LLMs
May 26, 2026Zhe Yu, Wenpeng Xing, Chen Ye +4Agentic Retrieval-Augmented Generation Systems Epistemic Asymmetry
Binjiang Institute of Zhejiang University · Zhejiang University · Hangzhou Dianzi University +1
On the evolution of the concept of probability as a mirror of the evolution of reason
May 26, 2026Jean-Louis Le Mouël, Vincent Courtillot, Dominique Gibert +6Dynamic Epistemic Logic Probability
Acad´emie des Sciences, Institut de France, Paris, France · DeepField Sensing, France · Institute of Earthquake Prediction Theory and Mathematical Geophysics, Russian Academy of Sciences, Moscow, Russia +4
Discoverable Agent Knowledge -- A Formal Framework for Agentic KG Affordances (Extended Version)
May 18, 2026Terry R. Payne, Valentina Tamma, Enrico DagaAgentic Discovery Ontology
School of Computer Science and Informatics, University of Liverpool, UK · Open University: Milton Keynes, Milton Keynes, UK
Sycophancy is an Educational Safety Risk: Why LLM Tutors Need Sycophancy Benchmarks
May 14, 2026Enkelejda Kasneci, Gjergji KasneciEpistemic Asymmetry Tutors
Technical University of Munich, Munich, Germany · Munich Center for Machine Learning, Munich, Germany
EnactToM: An Evolving Benchmark for Functional Theory of Mind in Embodied Agents
May 11, 2026Gurusha Juneja, Dylan Lu, Saaket Agashe +7Theory-Of-Mind Reasoning Embodied Agents
University of California, Santa Barbara · 2King’s College London · 3Cisco Research
Playing games with knowledge: AI-Induced delusions need game theoretic interventions
May 8, 2026Will Beaumaster, Paul SchraterEpistemic Asymmetry Game Theory
University of Minnesota
The Cost of Consensus: Malignant Epistemic Herding and Adaptive Gating in Distributed Multi-Agent Search
May 7, 2026David Farr, Iain Cruickshank, Kate Starbird +1Multi-Agent Coordination Multi-Agent Planning
1*Information School, University of Washington, 1410 NE Campus Parkway, Seattle, 98195, WA, USA. · 2Computer Science, Carnegie Mellon University, 5000 Forbes Avenue,2026 Pittsburgh, 15213, PA, USA. · 3Human Centered Design Engineering, University of Washington, 1410 NE Campus Parkway, Seattle, 98195, WA, USA. +1
Uncertainty Estimation in Instance Segmentation of Affordances via Bayesian Visual Transformers
May 5, 2026Lorenzo Mur-Labadia, Ruben Martinez-Cantina, Jose J. GuerreroUncertainty-Aware Classification Affordances
aI3A, Universidad de Zaragoza, Zaragoza, 50018, Spain
How Adversarial Environments Mislead Agentic AI?
Apr 20, 2026Zhonghao Zhan, Huichi Zhou, Zhenhao Li +3Adversarial Robustness Cyberattacks
Imperial College London
Compiling Deterministic Structure into SLM Harnesses
Apr 19, 2026Zan Kai Chong, Hiroyuki Ohsaki, Bryan NgLarge Language Model Workflows Small Large Language Models
School of Science and Technology Kwansei Gakuin University Japan · School of Engineering & Computer Science Victoria University of Wellington New Zealand
Beyond Memorization: Distinguishing Between Pattern-Based and Epistemic Reasoning in LLMs Using Epistemic Puzzles
Mar 22, 2026Adi Gabay, Gabriel Stanovsky, Liat PeterfreundEpistemic Asymmetry Epistemology
School of Computer Science and Engineering The Hebrew University of Jerusalem
Epistemic Bias Injection: Manipulating LLM Opinion via Selective Context Retrieval
Nov 30, 2025Hao Wu, Prateek SaxenaLarge Language Model Bias Attacker Large Language Model
National University of Singapore
From the Fluency Fallacy to the Micro-to-Macro Validity Gap: Opportunities and Pitfalls of LLMs in Social Simulation
Jul 25, 2025Patrick Taillandier, Jean Daniel Zucker, Arnaud Grignard +4Scaling Improve Social Simulation Agent-Based Model
UR MIAT, University of Toulouse, INRAE, Castanet-Tolosan, France · UMI UMMISCO, IRD, Sorbonne University, Bondy, France · UMR IRIT, University Toulouse Capitole, Toulouse, France +2

Aug 7, 2026, cs.CLJ/K move · Enter open · S save

Explicit, Not Longer: What Makes Epistemic Stance Survive Memory Compression

Alex Kwon

Independent Researcher

Epistemic Asymmetry Retention Stance Implicit Poetry

Open paper AskPDF arXiv

Agent memory systems compress what they store, and compression is built to drop qualifiers, so a claim's epistemic standing tends not to survive being written to memory. We ask what governs whether it does. Matched notes carry the identical claim and identical stance and differ only in where that stance sits; one model compresses both under the same budget among the same filler notes, and a blind reader that never sees the condition scores the result. Across 60 claims in seven registers, writing the stance as a labelled field rather than a bracketed aside raises retention by about 15 points on two models (37 claims to 2 on one, 30 to 8 on the other; permutation p=0.00005), and a pre-registered replication on Haiku, its prediction and decision rule committed before the run, gives +15.6 points, 38 claims to 1. Ablating the format on both models gives the same net effect from different parts: labels help on both (+9.7 and +12.8) and length helps on neither, but wording the stance as a full sentence is the largest component on one model (+12.5) and worth nothing on the other (+0.6). Either model alone would have licensed a confident and different mechanism, so we claim only the intersection: make the stance explicit, not merely longer, and expect the best way of being explicit to depend on the model. A deterministic readout with no model reproduces the two-cell direction and five of seven ablation contrasts, but not length or labels, which we therefore do not claim on one instrument. Fifty hand labels (kappa=0.75) agree on direction; we print their seven disagreements in full. We also report nine withdrawn claims, three of them former title claims of this paper.

Momentum

Related topics

Latest papers 26