Can LLMs Reason About Trust?: A Pilot Study
arxiv.org·5d
🤖Agents using LLMs
Curved Inference: Concern-Sensitive Geometry in Large Language Model Residual Streams
arxiv.org·5d
✨Model optimizations in LLMs
Efficient Differentially Private Fine-Tuning of LLMs via Reinforcement Learning
arxiv.org·4d
✨Model optimizations in LLMs
Towards Locally Deployable Fine-Tuned Causal Large Language Models for Mode Choice Behaviour
arxiv.org·5d
🔧Systems-level optimizations for LLM serving
Where to show Demos in Your Prompt: A Positional Bias of In-Context Learning
arxiv.org·4d
💬Prompt optimizations for LLM serving
Reviving Your MNEME: Predicting The Side Effects of LLM Unlearning and Fine-Tuning via Sparse Model Diffing
arxiv.org·5d
✨Model optimizations in LLMs
UloRL:An Ultra-Long Output Reinforcement Learning Approach for Advancing Large Language Models' Reasoning Abilities
arxiv.org·6d
💬Prompt optimizations for LLM serving
LoRA-PAR: A Flexible Dual-System LoRA Partitioning Approach to Efficient LLM Fine-Tuning
arxiv.org·6d
🔧Systems-level optimizations for LLM serving
Rethinking Evidence Hierarchies in Medical Language Benchmarks: A Critical Evaluation of HealthBench
arxiv.org·4h
📊AI Performance Profiling
AgriEval: A Comprehensive Chinese Agricultural Benchmark for Large Language Models
arxiv.org·5d
✨Model optimizations in LLMs
CLIPTime: Time-Aware Multimodal Representation Learning from Images and Text
arxiv.org·4h
⚡Real-time AI Systems
Survey of NLU Benchmarks Diagnosing Linguistic Phenomena: Why not Standardize Diagnostics Benchmarks?
arxiv.org·6d
💬Prompt optimizations for LLM serving
Graph Lineages and Skeletal Graph Products
arxiv.org·4h
🔍Retrieval-augmented generation
Exploring LLM-generated Culture-specific Affective Human-Robot Tactile Interaction
arxiv.org·3d
🔍Retrieval-augmented generation
Constructive Disintegration and Conditional Modes
arxiv.org·4h
✨Model optimizations in LLMs
Do Large Language Models Understand Morality Across Cultures?
arxiv.org·5d
✨Model optimizations in LLMs
StackLiverNet: A Novel Stacked Ensemble Model for Accurate and Interpretable Liver Disease Detection
arxiv.org·4h
⚡Real-time AI Systems
Tractable Responsibility Measures for Ontology-Mediated Query Answering
arxiv.org·3d
🔍Retrieval-augmented generation
From Individuals to Crowds: Dual-Level Public Response Prediction in Social Media
arxiv.org·4h
📊AI Performance Profiling
Toward using explainable data-driven surrogate models for treating performance-based seismic design as an inverse engineering problem
arxiv.org·4h
✨Model optimizations in LLMs