A Scalable Pipeline for Estimating Verb Frame Frequencies Using Large Language Models
arxiv.org·3d
✨Model optimizations in LLMs
The Pragmatic Mind of Machines: Tracing the Emergence of Pragmatic Competence in Large Language Models
arxiv.org·2d
💬Prompt optimizations for LLM serving
Discrete Tokenization for Multimodal LLMs: A Comprehensive Survey
arxiv.org·2d
🔢Quantization of LLMs
Uncovering the Fragility of Trustworthy LLMs through Chinese Textual Ambiguity
arxiv.org·2d
✨Model optimizations in LLMs
LENS: Learning Ensemble Confidence from Neural States for Multi-LLM Answer Integration
arxiv.org·2d
✨Model optimizations in LLMs
Smooth Reading: Bridging the Gap of Recurrent LLM to Self-Attention LLM on Long-Context Tasks
arxiv.org·6d
✨Model optimizations in LLMs
Enabling Few-Shot Alzheimer's Disease Diagnosis on Tabular Biomarker Data with LLMs
arxiv.org·2d
🔍Retrieval-augmented generation
The Geometry of Harmfulness in LLMs through Subconcept Probing
arxiv.org·4d
✨Model optimizations in LLMs
LLM-Crowdsourced: A Benchmark-Free Paradigm for Mutual Evaluation of Large Language Models
arxiv.org·3d
💬Prompt optimizations for LLM serving
CUS-QA: Local-Knowledge-Oriented Open-Ended Question Answering Dataset
arxiv.org·3d
💬Prompt optimizations for LLM serving
Good Learners Think Their Thinking: Generative PRM Makes Large Reasoning Model More Efficient Math Learner
arxiv.org·2d
🔍Retrieval-augmented generation
LLM-Assisted Cheating Detection in Korean Language via Keystrokes
arxiv.org·2d
💬Prompt optimizations for LLM serving
A Markov Categorical Framework for Language Modeling
arxiv.org·6d
✨Model optimizations in LLMs
Teaching Language Models To Gather Information Proactively
arxiv.org·4d
🔍Retrieval-augmented generation
CIMR: Contextualized Iterative Multimodal Reasoning for Robust Instruction Following in LVLMs
arxiv.org·3d
🔍Retrieval-augmented generation
Flora: Effortless Context Construction to Arbitrary Length and Scale
arxiv.org·5d
💬Prompt optimizations for LLM serving
Post-Training Large Language Models via Reinforcement Learning from Self-Feedback
arxiv.org·4d
✨Model optimizations in LLMs
Memorization in Fine-Tuned Large Language Models
arxiv.org·5d
🔍Retrieval-augmented generation
TriangleMix: A Lossless and Efficient Attention Pattern for Long Context Prefilling
arxiv.org·4d
⚡Real-time AI Systems
Trustworthy Reasoning: Evaluating and Enhancing Factual Accuracy in LLM Intermediate Thought Processes
arxiv.org·2d
💬Prompt optimizations for LLM serving