Large Language Models
GPT, Claude, Gemini, and other LLMs
Top This Week
Llms
Unsolved AI Mystery Is Solved Along With Lessons Learned On Why ChatGPT Became Oddly Obsessed With Gremlins And Goblins
This article discusses the resolution of an AI mystery regarding ChatGPT's unusual focus on gremlins and goblins, along with insights gai...
AI Tools & Products
·
1 min
·
Llms
When ChatGPT Learned I Have Cancer, It Started Treating Me Differently. I Wish It Hadn’t.
AI Tools & Products
·
8 min
·
All Content
![[2603.03378] AOI: Turning Failed Trajectories into Training Signals for Autonomous Cloud Diagnosis](https://arxiv.org/static/browse/0.3.4/images/arxiv-logo-fb.png){kind=logo}
Llms
[2603.03378] AOI: Turning Failed Trajectories into Training Signals for Autonomous Cloud Diagnosis
Abstract page for arXiv paper 2603.03378: AOI: Turning Failed Trajectories into Training Signals for Autonomous Cloud Diagnosis
arXiv - Machine Learning
·
4 min
·
Llms
[2603.03318] Quantum-Inspired Self-Attention in a Large Language Model
Abstract page for arXiv paper 2603.03318: Quantum-Inspired Self-Attention in a Large Language Model
arXiv - AI
·
3 min
·
Llms
[2603.03314] Towards Self-Robust LLMs: Intrinsic Prompt Noise Resistance via CoIPO
Abstract page for arXiv paper 2603.03314: Towards Self-Robust LLMs: Intrinsic Prompt Noise Resistance via CoIPO
arXiv - Machine Learning
·
4 min
·
Llms
[2603.03313] How does fine-tuning improve sensorimotor representations in large language models?
Abstract page for arXiv paper 2603.03313: How does fine-tuning improve sensorimotor representations in large language models?
arXiv - AI
·
3 min
·
Llms
[2603.03308] Old Habits Die Hard: How Conversational History Geometrically Traps LLMs
Abstract page for arXiv paper 2603.03308: Old Habits Die Hard: How Conversational History Geometrically Traps LLMs
arXiv - AI
·
3 min
·
Llms
[2603.03306] Token-Oriented Object Notation vs JSON: A Benchmark of Plain and Constrained Decoding Generation
Abstract page for arXiv paper 2603.03306: Token-Oriented Object Notation vs JSON: A Benchmark of Plain and Constrained Decoding Generation
arXiv - AI
·
4 min
·
Llms
[2603.03305] Draft-Conditioned Constrained Decoding for Structured Generation in LLMs
Abstract page for arXiv paper 2603.03305: Draft-Conditioned Constrained Decoding for Structured Generation in LLMs
arXiv - Machine Learning
·
3 min
·
Llms
[2603.03303] HumanLM: Simulating Users with State Alignment Beats Response Imitation
Abstract page for arXiv paper 2603.03303: HumanLM: Simulating Users with State Alignment Beats Response Imitation
arXiv - AI
·
4 min
·
Llms
[2603.03301] From Exact Hits to Close Enough: Semantic Caching for LLM Embeddings
Abstract page for arXiv paper 2603.03301: From Exact Hits to Close Enough: Semantic Caching for LLM Embeddings
arXiv - Machine Learning
·
3 min
·
Llms
[2603.03298] TATRA: Training-Free Instance-Adaptive Prompting Through Rephrasing and Aggregation
Abstract page for arXiv paper 2603.03298: TATRA: Training-Free Instance-Adaptive Prompting Through Rephrasing and Aggregation
arXiv - AI
·
4 min
·
Llms
[2603.03297] TTSR: Test-Time Self-Reflection for Continual Reasoning Improvement
Abstract page for arXiv paper 2603.03297: TTSR: Test-Time Self-Reflection for Continual Reasoning Improvement
arXiv - Machine Learning
·
4 min
·
Llms
[2603.03296] PlugMem: A Task-Agnostic Plugin Memory Module for LLM Agents
Abstract page for arXiv paper 2603.03296: PlugMem: A Task-Agnostic Plugin Memory Module for LLM Agents
arXiv - AI
·
4 min
·
Llms
[2603.03295] Language Model Goal Selection Differs from Humans' in an Open-Ended Task
Abstract page for arXiv paper 2603.03295: Language Model Goal Selection Differs from Humans' in an Open-Ended Task
arXiv - AI
·
3 min
·
Llms
[2603.03294] Fine-Tuning and Evaluating Conversational AI for Agricultural Advisory
Abstract page for arXiv paper 2603.03294: Fine-Tuning and Evaluating Conversational AI for Agricultural Advisory
arXiv - Machine Learning
·
4 min
·
Llms
[2603.03292] From Conflict to Consensus: Boosting Medical Reasoning via Multi-Round Agentic RAG
Abstract page for arXiv paper 2603.03292: From Conflict to Consensus: Boosting Medical Reasoning via Multi-Round Agentic RAG
arXiv - AI
·
4 min
·
Llms
[2603.03291] One Bias After Another: Mechanistic Reward Shaping and Persistent Biases in Language Reward Models
Abstract page for arXiv paper 2603.03291: One Bias After Another: Mechanistic Reward Shaping and Persistent Biases in Language Reward Models
arXiv - AI
·
3 min
·
Llms
[2603.03290] AriadneMem: Threading the Maze of Lifelong Memory for LLM Agents
Abstract page for arXiv paper 2603.03290: AriadneMem: Threading the Maze of Lifelong Memory for LLM Agents
arXiv - Machine Learning
·
4 min
·
Llms
[2603.04390] A Dual-Helix Governance Approach Towards Reliable Agentic AI for WebGIS Development
Abstract page for arXiv paper 2603.04390: A Dual-Helix Governance Approach Towards Reliable Agentic AI for WebGIS Development
arXiv - AI
·
3 min
·
Llms
[2603.04191] Towards Realistic Personalization: Evaluating Long-Horizon Preference Following in Personalized User-LLM Interactions
Abstract page for arXiv paper 2603.04191: Towards Realistic Personalization: Evaluating Long-Horizon Preference Following in Personalized...
arXiv - AI
·
3 min
·
Llms
[2603.04124] BeamPERL: Parameter-Efficient RL with Verifiable Rewards Specializes Compact LLMs for Structured Beam Mechanics Reasoning
Abstract page for arXiv paper 2603.04124: BeamPERL: Parameter-Efficient RL with Verifiable Rewards Specializes Compact LLMs for Structure...
arXiv - Machine Learning
·
4 min
·
Related Topics
Stay updated with AI News
Get the latest news, tools, and insights delivered to your inbox.
Daily or weekly digest • Unsubscribe anytime