It's LIT! Reliability-Optimized LLMs with Inspectable Tools
arxiv.org·18h
💬Natural Language Processing
Flag this post
October 2024 Progress in Guaranteed Safe AI
lesswrong.com·6h
∂Automatic Differentiation
Flag this post
Reducing MCP token usage by 100x – you don't need code mode
💬Natural Language Processing
Flag this post
A Comprehensive Study of Implicit and Explicit Biases in Large Language Models
arxiv.org·1d
💬Natural Language Processing
Flag this post
Bayesian Optimization in Language Space: An Eval-Efficient AI Self-Improvement Framework
arxiv.org·2d
∂Automatic Differentiation
Flag this post
Adversarial Poetry as a Universal Single-Turn Jailbreak Mechanism in Large Language Models
🤖Transformers
Flag this post
DNALONGBENCH: A benchmark suite for long-range DNA prediction tasks
💬Natural Language Processing
Flag this post
LLM-Driven Active Listwise Tournaments for Large Universe Portfolio Selection
🎯Optimization Theory
Flag this post
COMPASS: Context-Modulated PID Attention Steering System for Hallucination Mitigation
arxiv.org·18h
∂Automatic Differentiation
Flag this post
Empowering Multi-Turn Tool-Integrated Reasoning with Group Turn Policy Optimization
arxiv.org·18h
🎮Reinforcement Learning
Flag this post
Knowledge-Grounded Agentic Large Language Models for Multi-Hazard Understanding from Reconnaissance Reports
arxiv.org·1d
💬Natural Language Processing
Flag this post
Interpretable Ransomware Detection Using Hybrid Large Language Models: A Comparative Analysis of BERT, RoBERTa, and DeBERTa Through LIME and SHAP
arxiv.org·2d
🤖Transformers
Flag this post
All Your Coworkers Are Probabilistic Too
🔶TensorFlow
Flag this post
Loading...Loading more...