RetrievalAttention: Accelerating Long-Context LLM Inference via Vector Retrieval
Paper
•
2409.10516
•
Published
•
34
daily-papers
-
-
Measuring and Enhancing Trustworthiness of LLMs in RAG through Grounded Attributions and Learning to Refuse
Paper • 2409.11242 • Published • 5 -
Promptriever: Instruction-Trained Retrievers Can Be Prompted Like Language Models
Paper • 2409.11136 • Published • 21 -
On the Diagram of Thought
Paper • 2409.10038 • Published • 11 -
Video Instruction Tuning With Synthetic Data
Paper • 2410.02713 • Published • 33 -
Large Language Models as Markov Chains
Paper • 2410.02724 • Published • 28 -
Contrastive Localized Language-Image Pre-Training
Paper • 2410.02746 • Published • 28 -
Training Language Models on Synthetic Edit Sequences Improves Code Synthesis
Paper • 2410.02749 • Published • 12 -
L-CiteEval: Do Long-Context Models Truly Leverage Context for Responding?
Paper • 2410.02115 • Published • 10 -
Interpreting and Editing Vision-Language Representations to Mitigate Hallucinations
Paper • 2410.02762 • Published • 9 -
Layer Swapping for Zero-Shot Cross-Lingual Transfer in Large Language Models
Paper • 2410.01335 • Published • 5 -
RATIONALYST: Pre-training Process-Supervision for Improving Reasoning
Paper • 2410.01044 • Published • 34 -
Not All LLM Reasoners Are Created Equal
Paper • 2410.01748 • Published • 27 -
Quantifying Generalization Complexity for Large Language Models
Paper • 2410.01769 • Published • 12 -
InfiniPot: Infinite Context Processing on Memory-Constrained LLMs
Paper • 2410.01518 • Published • 2 -
Law of the Weakest Link: Cross Capabilities of Large Language Models
Paper • 2409.19951 • Published • 53 -
Hyper-Connections
Paper • 2409.19606 • Published • 18 -
Instruction Following without Instruction Tuning
Paper • 2409.14254 • Published • 26 -
LongGenBench: Long-context Generation Benchmark
Paper • 2410.04199 • Published • 16 -
Erasing Conceptual Knowledge from Language Models
Paper • 2410.02760 • Published • 12 -
Differential Transformer
Paper • 2410.05258 • Published • 150 -
LLMs Know More Than They Show: On the Intrinsic Representation of LLM Hallucinations
Paper • 2410.02707 • Published • 44 -
Addition is All You Need for Energy-efficient Language Models
Paper • 2410.00907 • Published • 130 -
Selective Attention Improves Transformer
Paper • 2410.02703 • Published • 22 -
Mentor-KD: Making Small Language Models Better Multi-step Reasoners
Paper • 2410.09037 • Published • 4 -
Rethinking Data Selection at Scale: Random Selection is Almost All You Need
Paper • 2410.09335 • Published • 11 -
StructRAG: Boosting Knowledge Intensive Reasoning of LLMs via Inference-time Hybrid Information Structurization
Paper • 2410.08815 • Published • 30 -
SuperCorrect: Supervising and Correcting Language Models with Error-Driven Insights
Paper • 2410.09008 • Published • 15 -
Mechanistic Permutability: Match Features Across Layers
Paper • 2410.07656 • Published • 16 -
SimpleStrat: Diversifying Language Model Generation with Stratification
Paper • 2410.09038 • Published • 3 -
PositionID: LLMs can Control Lengths, Copy and Paste with Explicit Positional Awareness
Paper • 2410.07035 • Published • 16