ProCut: LLM Prompt Compression via Attribution Estimation
arxiv.org·18h
🧠Large Language Models (LLMs)
MOPrompt: Multi-objective Semantic Evolution for Prompt Optimization
arxiv.org·18h
🧠Large Language Models (LLMs)
Optimal Scheduling Algorithms for LLM Inference: Theory and Practice
arxiv.org·18h
🔧Systems-level optimizations for LLM serving
Beyond Manually Designed Pruning Policies with Second-Level Performance Prediction: A Pruning Framework for LLMs
arxiv.org·18h
🔧Systems-level optimizations for LLM serving
Refine-n-Judge: Curating High-Quality Preference Chains for LLM-Fine-Tuning
arxiv.org·18h
🧠Large Language Models (LLMs)
Test-time Prompt Intervention
arxiv.org·18h
🔍Retrieval-augmented generation
How to Enhance RAG Pipelines with Reasoning Using NVIDIA Llama Nemotron Models
developer.nvidia.com·4d
🧠Large Language Models (LLMs)
CAPO: Towards Enhancing LLM Reasoning through Verifiable Generative Credit Assignment
arxiv.org·18h
🧠Large Language Models (LLMs)
PromptSafe: Gated Prompt Tuning for Safe Text-to-Image Generation
arxiv.org·18h
🔍Retrieval-augmented generation
PilotRL: Training Language Model Agents via Global Planning-Guided Progressive Reinforcement Learning
arxiv.org·1d
🧠Large Language Models (LLMs)
Learning an Efficient Multi-Turn Dialogue Evaluator from Multiple Judges
arxiv.org·1d
🧠Large Language Models (LLMs)
A Methodological Framework for LLM-Based Mining of Software Repositories
arxiv.org·18h
🧠Large Language Models (LLMs)
Prompting Science Report 3: I'll pay you or I'll kill you -- but will you care?
arxiv.org·1d
🧠Large Language Models (LLMs)
Confidence-Diversity Calibration of AI Judgement Enables Reliable Qualitative Coding
arxiv.org·18h
🧠Large Language Models (LLMs)
SynAdapt: Learning Adaptive Reasoning in Large Language Models via Synthetic Continuous Chain-of-Thought
arxiv.org·1d
🧠Large Language Models (LLMs)
ProKG-Dial: Progressive Multi-Turn Dialogue Construction with Domain Knowledge Graphs
arxiv.org·18h
🧠Large Language Models (LLMs)
Autonomous Penetration Testing: Solving Capture-the-Flag Challenges with LLMs
arxiv.org·18h
🔧Systems-level optimizations for LLM serving
TRACEALIGN -- Tracing the Drift: Attributing Alignment Failures to Training-Time Belief Sources in LLMs
arxiv.org·18h
🧠Large Language Models (LLMs)
Attractive Metadata Attack: Inducing LLM Agents to Invoke Malicious Tools
arxiv.org·18h
🤖Agents using LLMs
KCR: Resolving Long-Context Knowledge Conflicts via Reasoning in LLMs
arxiv.org·18h
🧠Large Language Models (LLMs)