Ablation

Ask about this topic

Recent momentum

-47%

8 papers in the last 28 days · 0.1% of indexed attention

Twelve weeks of publication activity for this topic as it is defined today.

Weekly history

Recent digests

What was published in this topic, kept on the site without email delivery.

Period ending 2026-09-21

2 new papers

A weekly snapshot of new work published in Ablation.

Period ending 2026-09-14

4 new papers

A weekly snapshot of new work published in Ablation.

Period ending 2026-09-07

2 new papers

A weekly snapshot of new work published in Ablation.

96 papers

Latest in Ablation

Browse all topics →
CardsList

  1. What You Can't See Is Still What You Learn: A Preregistered Sixty-Society Confirmation That Evidence Masking Drives Compositional Generalization

    Sep 15, 2026Narcis MarincatAblationRelation-Conditioned Evidence Encoder

  2. Negation Beyond the Verbal Channel: Temporal Multimodal Correlates in Dialogue

    Sep 14, 2026Leon Hammerla, Patrick Schrottenbacher, Alexander MehlerNonverbal CuesNegation

  3. Domain-Specific Hallucination Detection in Large Language Models

    Sep 12, 2026Varun Teja Chundru, Debasmita BiswasHallucination DetectionHallucinations

  4. How Fragile Is Safety Alignment at Frontier Scale? A Single-Direction Attack on a 320B MoE

    Sep 9, 2026Yi Shi, Tanyu Chen, Kai ShenLarge Language Model AlignmentSafety Alignment

  5. Evaluating and Improving Evidence-Grounded Fact-Checking in LLMs via Multi-Round Evidence Ablation

    Sep 8, 2026Xingyu Deng, Mingzi Cao, Nikolaos Aletras +2Fact-CheckingCounterfactual Learning

  6. The Gradient Does Not See Rank: Rank-Indifference in Matrix-CODI on ProsQA

    Sep 2, 2026Samuel LarsonLow-Rank FactorizationRanking

  7. Compression-Aware Abstention: Teaching LLMs to Refuse When KV-Compression Masks Remove Answer Evidence

    Aug 30, 2026Mohammadali Khodabandehlou, Bhaskar KrishnamachariLLM Inference EfficiencyAblation

  8. Activation-Weighted Seeded Residual Coding for Low-Bit LLM Weight Repair

    Aug 24, 2026Zehao Liu, Chuangchuang Fang, Yang RenModel WeightsLarge Language Model Decoder

  9. Where You Measure Decides What You Measure: Position Selection in Ablation-Based SAE Evaluation

    Aug 13, 2026Valentin NoëlAblationLegal Natural Language Processing Benchmarks

  10. Perturbation-based Regional Interpretability through Subtraction Mapping (PRISM): naming-error dissociations in language models and post-stroke aphasia

    Aug 13, 2026Xiang Guan, Roger D. Newman-Norlund, Yong Yang +8DissociationDysarthric Speech

  11. Hybrid Neural-Classical Correction for Frozen Time Series Foundation Models: A Comprehensive Ablation Study on High-Frequency Stock Prediction

    Aug 9, 2026Kasun Dewage, Suranadi De Silva, Shankhadeep MondalTime Series Foundation ModelsStochastic Volatility

  12. Which Decisions Low-Bit Quantization Breaks, and How to Predict Them

    Aug 6, 2026Zekun Wu, Swati Dhiman, Adriano KoshiyamaQuantizationDecisions

  13. The Price of Isolation: Estimating the Ecosystem Cost of Symmetric Two-Sided A/B Testing

    Aug 5, 2026Yuanyuan Shen, Yiren Yan, Wenjie Li +1PricesControlled Study

  14. Sparse Weight Decomposition for Efficient Circuit Extraction

    Aug 4, 2026Chuanhao Yan, Xuhan Huang, Yawen Duan +4Model WeightsTransformer Architectures

  15. Cross-Layer Interaction under Weight-Space Ablation: A Closed-Form Attention Jacobian Bound and a Test on a Real Pretrained Model

    Aug 4, 2026Abdallah KhemaisAblationCross-Layer Interactions

  16. A Theory of Conditional Collapse under Low-Rank Weight-Space Ablations: I. The Single-Block Theory and Synthetic Validation

    Aug 4, 2026Abdallah KhemaisAblationCollapse

  17. Automatic Patient-Specific Microwave Ablation Planning Accelerated by a Physics-Guided Deep Learning Model

    Aug 4, 2026Seonaeng Cho, Minjee Seo, Minju Seol +3RadiotherapyCholangiocarcinoma

  18. Caliber: Cross-Architecture Extraction-Cost Control for Score-Returning APIs

    Aug 2, 2026Chi Wang, Hanwen Wang, Yu Xia +2AblationCross-Architecture Generalization

  19. CT-HEG: A Bidirectional, Timestamp-Attributed Event Graph for ICU In-Hospital Mortality Prediction - An Architectural Ablation Study

    Aug 1, 2026Mohammad Nasir Uddin, Rahnuma Tabassum Orpita, Asaduzzaman Anik +4MortalitySequence Modeling

  20. Faster but Different: Diagnosing and Controlling Content Drift in Accelerated Multimodal Diffusion Language Models

    Jul 31, 2026Yaoxuan Dou, Yang ShuDiffusion Language ModelsTraining-Inference Mismatch

  21. What Makes Deep Learning Work for Traditional Chinese Medicine Tongue Diagnosis? A Comprehensive Ablation Study

    Jul 30, 2026Longxia Gao, Linan Wang, Yuhe Han +3Medical Image ClassificationDeep Learning

  22. A Montage-Agnostic Encoder for Calibration-Light Cross-User Gesture Recognition from Surface Electromyography

    Jul 30, 2026Jethro Odeyemi, W. J. ZhangHand Gesture RecognitionLegs

  23. Do Context Files Help Coding Agents? A Two-Agent Ablation Study on Real Repositories

    Jul 28, 2026Prakhar KhatriCoding AgentsInjecting

  24. Where Facts Go Missing: A Layerwise Taxonomy and Per-Layer Attribution of Information Omission in Air-Gapped LLMAgent Pipelines

    Jul 24, 2026Santhiya RajanAblationFalsehood

  25. Circuit Claims Depend on What Is Extracted and How It Is Compared

    Jul 21, 2026Yang Sheng, Jie FuCircuitsAblation

  26. Reasoning Fine-Tuning Induces Persistent Latent Policy States

    Jul 20, 2026Abir Harrasse, Michael Lan, Hunar Batra +2Ablation

  27. Abliteration Is Not a Scalpel: Off-Target Effects of Refusal Removal on Decision Disposition Across Model Families

    Jul 19, 2026Aleksander FafułaAblationRefusals

  28. AEGIS: Assay-Aware Protocol Validation and Runtime Monitoring for Open-Source Liquid Handling Robots

    Jul 17, 2026Priyanka V. Setty, Arvind Ramanathan, Ian Foster +1Human-In-The-LoopValidity

  29. Local Additive Feature Attribution: A Mathematical Taxonomy and Reporting Checklist

    Jul 15, 2026Rebecca Afriyie Sarpong, Daniel CommeyExplainable Artificial IntelligenceAblation

  30. VanillaBench: The Hidden Accuracy Cost of Adversarial Robustness

    Jul 14, 2026Niklas BunzelCross-Architecture GeneralizationAblation

  31. When Does Restricting a Coding Agent to execute_code Help? A Regime ×\times Agent-Design Ablation

    Jul 12, 2026Hong Yang, Qi Yu, Travis DesellCoding AgentsAblation

  32. Byzantine Accountability Without Consensus: Strong Eventual Consistency for Non-Associative, Stochastic, Robust Aggregation

    Jul 11, 2026Ryan GillespieByzantine AttacksConsensus

  33. TopoExplore: Topological Discrimination for Archive-Based Exploration

    Jul 10, 2026Jason CarlsonAutonomous Exploration StrategiesTopological Data Analysis

  34. Can We Trust LLM's Logic? Quantifying Uncertainty, Coherence, and Robustness via a Graph-Based Framework

    Jul 9, 2026Riccardo Revalor, Jalees Rehman, Debjit PalLarge Language Model ReasoningSelf-Consistency

  35. Context-Aware Slum Mapping in Sub-Saharan Africa Using Sentinel-1 Texture and Local Climate Zones

    Jul 8, 2026Peterson Chepkilot, Babak Memar, Paolo GambaSentinel-2Urban Environments

  36. Progressive Disclosure for LLM-Maintained Wiki Knowledge Bases: a Preregistered Ablation

    Jul 6, 2026Theodore O. CochranWikipediaProcedural Knowledge

  37. Deep Learning-Based Characterization of Detonation-Cell Size Distributions in Soot-Foil Records

    Jul 4, 2026Mingyang Bu, Robson A. Schneider, Karl P. Chatelain +5Inertial Confinement FusionAblation

  38. Not All Refusals Are Equal: How Safety Alignment Fails Cybersecurity at Scale

    Jul 2, 2026Vadym Hadetskyi, Dario Pasquini, Artem SorokinSafety AlignmentCybersecurity

  39. Fast Multi-dimensional Refusal Subspaces via RFM-AGOP

    Jul 2, 2026Thomas WinningerRefusalsReasoning Traces

  40. Conditional Co-Ablation: Recovering Self-Repair Backups in Transformer Circuits

    Jul 2, 2026Zhiren Gong, He Lu, Tiantong Wang +6AblationMechanistic Interpretability

  41. The Contagion Tensor: A Framework for Measuring Output-Distribution Coupling in Multi-Agent LLM Systems -- and Auditing the Claims It Enables

    Jun 27, 2026Zewen LiuMulti-Agent Large Language Model SystemsAblation

  42. Reproducibility Study of "AlphaEdit: Null-Space Constrained Knowledge Editing for Language Models"

    Jun 25, 2026Ananth K Suresh, Arya HariharanMultimodal Knowledge EditingDiffusion Editing

  43. NebulaExp-8B: An Empirical Post-Training Pipeline via Full-Scale Ablation Research

    Jun 25, 2026Qiaobo Hao, Yangqian Wu, Shunyi Wang +5Large Language Model Post-TrainingLLM Post-Training Methods

  44. The Inattentional Gap: Task-Conditioned Language and Vision Models Omit the Safety-Critical Signals They Can Otherwise Report

    Jun 25, 2026Kwan Soo Shin, In Seok Kang, Yunkyung Min +2Artificial Intelligence SafetyBlind Spots

  45. Retrieval-Warmed Energy-Based Reasoning: A Five-Arm Ablation Methodology for Diffusion-as-Inference on Structured Reasoning Tasks

    Jun 25, 2026Libo Sun, Po-Wei Harn, Zewei Zhang +2Discrete Diffusion ModelAblation

  46. TrOCR for Medieval HTR: A Systematic Ablation Study with Cross-Dataset Validation

    Jun 23, 2026Sachin Sharma, Michele Flammini, Federico SimonettaHandwritten Text RecognitionModernbert

  47. A Leakage-Aware Comparative Benchmark of Machine Learning, Deep Learning, and Transformer Models for Reliable Leukemia Detection

    Jun 23, 2026Nisreen AlbzourAcute Myeloid LeukemiaAuc-Roc

  48. Context-Aware Distillation and Ablation for Text2DSL

    Jun 21, 2026Alexander V. Kozachok, Alexander M. Nazimov, Shamil G. MagomedovDomain-Specific LanguageChain-Of-Thought Distillation

  49. First-Token Broadcasters: Mechanistic Origins of Language Identity and Distributed Robustness in Transformers

    Jun 21, 2026Arjun Pillai, Christian Hoang, Anjelo Jann LarozaEnglishInstruction-Tuned Models

  50. Dissecting Agentic RAG: A Component Ablation for Multi-Hop QA with a Local 7B Model

    Jun 19, 2026Sheroz ShaikhRetrieval-Augmented Generation SystemsMulti-Hop Reasoning

  51. Task-Restricted Symmetries in Recurrent Weight Space

    Jun 16, 2026Simon DrägerRecurrent Neural NetworksWeight-Space

  52. Pointwise is Pointless? A Multimodal Ablation Study for Precipitation Nowcasting with Graph Neural Networks

    Jun 16, 2026Ophélia Miralles, Máté Mile, Christoffer Artturi +2PrecipitationRadar

  53. Assessing Reliability of Symbol Detection in Concept Bottleneck Models

    Jun 15, 2026Javier Fumanal-Idocin, Javier Andreu-PerezConcept Bottleneck ModelsExplainable Artificial Intelligence

  54. Lost at the End: Primacy Bias in Multimodal Retrieval-Augmented Question Answering

    Jun 15, 2026Jieyuan Liu, Jianyang Gu, Shijie Chen +2Knowledge-Based Visual Question AnsweringMultimodal Learning

  55. Ablation, Statistical Inference, and Validation for KV-Cache Compression

    Jun 14, 2026Paolo D'Alberto, Ashish Siarasao, Elliott Delaye +1Key-Value Cache CompressionCalibration-Free Low-Bit Vector Quantization

  56. FinBalance: A Multi-Document Accounting Reconciliation Benchmark

    Jun 14, 2026Sasank Tumpati, Devansh Agarwal, Ayush Kedia +6Finance DomainLegal Natural Language Processing Benchmarks

  57. Beyond Importance: Interchange-Sobol Sensitivity Reveals Task-Specific Content Channels in Transformer Components

    Jun 12, 2026Yifeng Guo, Jin-Hong Du, Xiang ChenTransformer ArchitecturesImportance

  58. Human genetic evidence is associated with drug approval across therapeutic areas: an observational analysis of 26,278 target-disease pairs with temporal validation and feature ablation

    Jun 12, 2026Victoria PatersonAblation

  59. SANA: What Matters for QA Agents over Massive Data Lakes?

    Jun 11, 2026Austin Senna Wijaya, Jiaxiang Liu, Haonan Wang +1Data LakesMulti-Hop Question Answering Benchmarks

  60. Closure-Validated Circuit Discovery in Attention Heads: Co-activation Proposes, Ablation Disposes

    Jun 8, 2026Yongzhong XuAblationCircuits