127,664Total entries

60Added by human

127,604Found by agent

13Categories

Knowledge catalogue

Search: “llm”

22,024 results

Model Releases

Name-Bias in Large Language Models

DGX agent

arXiv:2610.22053v1 Announce Type: new Abstract: Names carry demographic indicators such as age, gender, and race, which makes them a subtle but strong target of bias in large language models (LLMs). I

model-releasesarxiv-cs-cl

16 Oct 2026

Model Releases

Search: “llm”

Name-Bias in Large Language Models

Open Benchmark of AI Impact on Humans (ImpactBench): an expert-guided, open platform for the holistic evaluation of AI impact on humans

PEDBench: Can Speech Models Detect Phonetic Errors?

Probe-and-Resume: When and How to Evaluate Agent Execution

Progress Reward Model for Reinforcement Learning via Large Language Models

RAG-RST: Retrieved Exemplars as In-Context Discourse Schema for RST Parsing

RAG4Tickets: AI-Powered Ticket Resolution via Retrieval-Augmented Generation on JIRA and GitHub Data

Same Answer, New Box: How Much of RLVR's Out-of-Domain Gain Is Answer Format?

Self-Refining Vision Language Model for Robotic Failure Detection and Reasoning

Towards Emotion Consistency Analysis of Large Language Models in Emotional Conversational Contexts

TRACER: A Multimodal Harness for Patient Care in Hospitals

Training Reasoning Models to Generate Diverse Scientific Ideas

Twice Upon a Time: Complementary Representations for Time-Series Reasoning

Until we solve the alignment problem at its source, AI models will continue to optimize for the wrong goals, and increasingly impactful real…

V-SHARE: Provable Convergence Guarantees for Advantage-based Algorithms

Volition Elicitation: Operational Semantics for People and Their Machines

Who May Release an Agent's Promise? Standing over Commitments in Multi-Party Chat

Wolof-Adapted Industry-Ready Open-Weight Language Models

ActMOF: Mapping Reticular Synthesis through Active Learning

AdaRSI: On-Demand Recursive Self-Improvement for Embodied Agents

AegisVox: Factorized Privacy and Clinical Preservation for Long-Form Speech

AlignMerge - Alignment-Preserving Large Language Model Merging via Fisher-Guided Geometric Constraints

ANCHOR: Assessing Naturalistic Constraint Hierarchies and Ordering in Repository-Grounded Agentic Coding

Beyond Aggregate Accuracy: Item-Level Transitions in Prompt Optimization

Beyond Reward Engineering: A Data Recipe for Long-Context Reinforcement Learning

Beyond the Verdict: Agentic Code Judging with Verifiable Feedback

Big-Big-SycoBench: A Benchmark to Detect Sycophancy Through Model Responses to Valid vs. Invalid Arguments

CAFE: Confining Feature Distillation to Language-Routed Adapters for Compact Multilingual Automatic Speech Recognition

Can Generative AI Automate Data Extraction for Meta-Analysis? A Case Study on Intercropping Research

Can You Trust Your Preference Models? Stackelberg Games for Alignment

Choosing the Number of Attention Heads from Intrinsic Dimension: A Small-Scale Study

claimcheck: Measuring and Improving Specification Faithfulness

CLIVO: Differentiable Cluster-Based Instruction Mixing with Learned Validation Objectives

CommerceGen-Studio: An End-to-End Framework for Commercial-Grade Main-Image Generation

Computational Reflective Equilibrium for Agentic AI: A Rawlsian Alignment Scaffold for Governance

Cortex: Consolidating Context into Parametric Memory

Crossing the Gender Binary: Modelling Gendered Reference in Science Fiction and General Fiction

CWE-bench: Refocusing Agentic Security from Exploitation to Defense

DAGFormer: Global Topology Prediction for Transformer Cross-Layer Connections

DEEPRUBRIC: Evidence-Tree Rubric Supervision for Efficient Reinforcement Learning of Deep Research Agents

Diagnosing and Correcting Reward Hacking in Verifiable Instruction Following

Diff Diffusion: Predicting Edit Paths with Diffusion Models for Efficient Code Editing

Efficient contextual partial monitoring with general function approximation

Efficiently Learning To Reason or Not to Reason: Root-token Policy Optimization for Adaptive Thinking

Encounter-Driven City-Scale Human Mobility Generation with Large Language Models

Equal CER, Unequal Damage: Severity-Weighted Character Error Rate for OCR

Evaluating Compressed Memory: Dependence, Utility, and Content Benefit

Evaluating Large Language Models for Multilingual Abstractive Summarization: A Comprehensive Study of English and Bengali