MRGSEM-Sum: An Unsupervised Multi-document Summarization Framework based on Multi-Relational Graphs and Structural Entropy Minimization
arxiv.org·2d
🔍Retrieval-augmented generation
A Gold Standard Dataset and Evaluation Framework for Depression Detection and Explanation in Social Media using LLMs
arxiv.org·5d
🔍Retrieval-augmented generation
Whilter: A Whisper-based Data Filter for "In-the-Wild" Speech Corpora Using Utterance-level Multi-Task Classification
arxiv.org·4d
⚡Real-time AI Systems
Uncovering Cross-Linguistic Disparities in LLMs using Sparse Autoencoders
arxiv.org·6d
✨Model optimizations in LLMs
Can LLMs Reason About Trust?: A Pilot Study
arxiv.org·4d
🤖Agents using LLMs
Curved Inference: Concern-Sensitive Geometry in Large Language Model Residual Streams
arxiv.org·4d
✨Model optimizations in LLMs
Efficient Differentially Private Fine-Tuning of LLMs via Reinforcement Learning
arxiv.org·3d
✨Model optimizations in LLMs
Exploring LLM-generated Culture-specific Affective Human-Robot Tactile Interaction
arxiv.org·2d
🔍Retrieval-augmented generation
Towards Locally Deployable Fine-Tuned Causal Large Language Models for Mode Choice Behaviour
arxiv.org·4d
🔧Systems-level optimizations for LLM serving
Where to show Demos in Your Prompt: A Positional Bias of In-Context Learning
arxiv.org·3d
💬Prompt optimizations for LLM serving
Reviving Your MNEME: Predicting The Side Effects of LLM Unlearning and Fine-Tuning via Sparse Model Diffing
arxiv.org·4d
✨Model optimizations in LLMs
UloRL:An Ultra-Long Output Reinforcement Learning Approach for Advancing Large Language Models' Reasoning Abilities
arxiv.org·5d
💬Prompt optimizations for LLM serving
LoRA-PAR: A Flexible Dual-System LoRA Partitioning Approach to Efficient LLM Fine-Tuning
arxiv.org·5d
🔧Systems-level optimizations for LLM serving
AgriEval: A Comprehensive Chinese Agricultural Benchmark for Large Language Models
arxiv.org·4d
✨Model optimizations in LLMs
Survey of NLU Benchmarks Diagnosing Linguistic Phenomena: Why not Standardize Diagnostics Benchmarks?
arxiv.org·5d
💬Prompt optimizations for LLM serving
Improving annotator selection in Active Learning using a mood and fatigue-aware Recommender System
arxiv.org·2d
✨Model optimizations in LLMs
Do Large Language Models Understand Morality Across Cultures?
arxiv.org·4d
✨Model optimizations in LLMs
Tractable Responsibility Measures for Ontology-Mediated Query Answering
arxiv.org·2d
🔍Retrieval-augmented generation
MemTool: Optimizing Short-Term Memory Management for Dynamic Tool Calling in LLM Agent Multi-Turn Conversations
arxiv.org·4d
🤖Agents using LLMs
A novel language model for predicting serious adverse event results in clinical trials from their prospective registrations
arxiv.org·2d
🔍Retrieval-augmented generation