Browse all

arXiv research papers — all

All arXiv papers (AI/ML focus) — filter and search by category and year.

Clear

416 results

PaperCategoryAuthorsDate
What Does a Bias Head Measure? Non-Identifiability in Head-Level... ↗ cs.CL 1 Nov 17, 2026
Structure--Residual Inductive Biases for Language Model Pretrain... ↗ cs.CL 5 Nov 17, 2026
Polarity Composition Hypothesis: Causal Evidence from Negation i... ↗ cs.CL 4 Nov 17, 2026
MoE--LoRA Methods for Multilingual Adaptation: A Systematic Empi... ↗ cs.CL 4 Nov 17, 2026
Dynamic Task Allocation with Dialogue ↗ cs.CL 3 Nov 17, 2026
Natural Language Programming: Rethinking Language, Memory, and C... ↗ cs.CL 2 Nov 17, 2026
What's in a Tree ? Hierarchical $n$-gram models as controlled ap... ↗ cs.CL 6 Nov 17, 2026
Runtime Verification of Multiple Natural Language Criteria for A... ↗ cs.CL 5 Nov 17, 2026
TPHC: Improving Hyper-Connections with Tensor-Parallel Grouped U... ↗ cs.CL 7 Nov 17, 2026
Large Language Models Have Not Yet Transformed Science ↗ cs.CL 4 Nov 17, 2026
Can Decision Models Replace LLMs in Real-World Contact Center Cl... ↗ cs.CL 3 Nov 17, 2026
The Shared Word: Evaluating Language Models on Dutch Word Puzzle... ↗ cs.CL 2 Nov 17, 2026
When Do Typed Decision Models Work in Transportation? Evidence f... ↗ cs.CL 5 Nov 17, 2026
When Passing Checks Do Not Establish Completion: Evidence Interp... ↗ cs.CL 1 Nov 17, 2026
Compact and Decodable Electrocardiogram Text for Large Language... ↗ cs.CL 2 Nov 17, 2026
Mechanistic Interpretability Needs a Logic of Inference ↗ cs.CL 5 Nov 10, 2026
Pterodactyl: Pushing the Limits of Efficient Automated Translati... ↗ cs.CL 2 Nov 10, 2026
When does text encoding matter for language modeling? ↗ cs.CL 3 Nov 10, 2026
Blurring the Block Boundaries: Overlapping Block Denoising for E... ↗ cs.CL 7 Nov 10, 2026
ARE-bench: Benchmarking Agents' Research Ability in Real-World R... ↗ cs.CL 27 Nov 10, 2026
Point-in-Time Encoders for Earnings Calls ↗ cs.CL 1 Nov 10, 2026
Semantic Chains: From Reachable Facts to Justified Answers ↗ cs.CL 1 Nov 10, 2026
An AI Assistant for Automating Anti-Corruption Expertise of Draf... ↗ cs.CL 2 Nov 10, 2026
Dyship: Leveraging Acoustic Features For Speaker Relationship Cl... ↗ cs.CL 4 Nov 10, 2026
StaRSE: Compact Russian Sentence Embeddings with a Sign-Coded St... ↗ cs.CL 9 Nov 10, 2026
Stagewise and interpretable emergence of inside-outside computat... ↗ cs.CL 1 Nov 10, 2026
Representational Atoms in Neural Networks ↗ cs.CL 4 Nov 10, 2026
Visual Similarity in Adult Word Extension and Artificial Word Le... ↗ cs.CL 1 Nov 10, 2026
Sckwoky at SHROOM-Visions: Character-Level Hallucination-Span De... ↗ cs.CL 3 Nov 10, 2026
From Bias to Positionality: A critical grammar for Large Languag... ↗ cs.CL 4 Nov 10, 2026
HandsOnAid: Building and Evaluating an Offline First-Aid Assista... ↗ cs.CL 3 Nov 10, 2026
MISO-BR: An Open Corpus for Misogyny Detection in Brazilian Port... ↗ cs.CL 3 Nov 10, 2026
Program-Aided Patchable Skill Evolution ↗ cs.CL 7 Nov 10, 2026
One Sequence Is Enough: Fingerprinting Language Models from Fixe... ↗ cs.CL 6 Nov 10, 2026
From Autonomous Agents to Cognitive Symbionts: Toward AI-Augment... ↗ cs.CL 1 Nov 3, 2026
Suppressing Misaligned Behaviors in Language Models, Durably ↗ cs.CL 5 Nov 3, 2026
A Circuit for In-Context Learning ↗ cs.CL 2 Nov 3, 2026
MDSKILL: Learning to Internalize Skill Memory through Multi-View... ↗ cs.CL 12 Nov 3, 2026
Personas Are Not People: Identity as State, Not Attribute ↗ cs.CL 2 Nov 3, 2026
Knowingly Wrong: Training LLMs Against Their Own Beliefs can Ind... ↗ cs.CL 4 Nov 3, 2026
Beyond Accuracy: What Language-Subspace Interventions Capture, R... ↗ cs.CL 5 Nov 3, 2026
ARLoop: Fully-Open Pre-trained Looped Transformers with Attentio... ↗ cs.CL 4 Nov 3, 2026
When Self-Verification Hurts: Calibrated Answer Repair for Finan... ↗ cs.CL 7 Nov 3, 2026
GM League Arena: An Interactive Long-Horizon Task Benchmark Base... ↗ cs.CL 3 Nov 3, 2026
The Right Source Is Not Enough: Understanding History Interferen... ↗ cs.CL 14 Nov 3, 2026
ToolSpace: Scaling Tool-Centric Environment Synthesis for Long-H... ↗ cs.CL 25 Nov 3, 2026
Whose Effect Is It? How Objectives Inflate Learned Subspace Inte... ↗ cs.CL 2 Nov 3, 2026
Who is the Pronoun Pro? Comparing LLMs and Humans at Number-Disa... ↗ cs.CL 1 Nov 3, 2026
Shuffled OPSD: When Semantic Consistency Hurts On-Policy Self-Di... ↗ cs.CL 2 Nov 3, 2026
HERIT: Enabling Global Access to Hanja-to-English Historical Tra... ↗ cs.CL 2 Nov 3, 2026

Source: official U.S. government open data. This is an organized index, not an official U.S. government site. "Explained" links to our summary page; otherwise links go to the official primary source.

Disclaimer: This site independently summarizes and classifies information based on official data sources. Always verify the latest and accurate information with the official sources. Content on finance, health, legal, and security is information, not advice. This site is not an official website of the U.S. government.