-
Unlocking Continual Learning Abilities in Language Models
Paper • 2406.17245 • Published • 27 -
A Closer Look into Mixture-of-Experts in Large Language Models
Paper • 2406.18219 • Published • 15 -
Symbolic Learning Enables Self-Evolving Agents
Paper • 2406.18532 • Published • 10 -
Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs
Paper • 2406.18629 • Published • 38
Collections
Discover the best community collections!
Collections including paper arxiv:2407.00320
-
Eliminating Position Bias of Language Models: A Mechanistic Approach
Paper • 2407.01100 • Published • 6 -
To Forget or Not? Towards Practical Knowledge Unlearning for Large Language Models
Paper • 2407.01920 • Published • 13 -
LiteSearch: Efficacious Tree Search for LLM
Paper • 2407.00320 • Published • 37
-
Octo-planner: On-device Language Model for Planner-Action Agents
Paper • 2406.18082 • Published • 47 -
Adaptable Logical Control for Large Language Models
Paper • 2406.13892 • Published • 1 -
SeaKR: Self-aware Knowledge Retrieval for Adaptive Retrieval Augmented Generation
Paper • 2406.19215 • Published • 29 -
HippoRAG: Neurobiologically Inspired Long-Term Memory for Large Language Models
Paper • 2405.14831 • Published • 3
-
How Do Large Language Models Acquire Factual Knowledge During Pretraining?
Paper • 2406.11813 • Published • 29 -
From RAGs to rich parameters: Probing how language models utilize external knowledge over parametric information for factual queries
Paper • 2406.12824 • Published • 20 -
Tokenization Falling Short: The Curse of Tokenization
Paper • 2406.11687 • Published • 14 -
Iterative Length-Regularized Direct Preference Optimization: A Case Study on Improving 7B Language Models to GPT-4 Level
Paper • 2406.11817 • Published • 13
-
Same Task, More Tokens: the Impact of Input Length on the Reasoning Performance of Large Language Models
Paper • 2402.14848 • Published • 18 -
The Prompt Report: A Systematic Survey of Prompting Techniques
Paper • 2406.06608 • Published • 52 -
CRAG -- Comprehensive RAG Benchmark
Paper • 2406.04744 • Published • 40 -
Transformers meet Neural Algorithmic Reasoners
Paper • 2406.09308 • Published • 43
-
Language Models as Compilers: Simulating Pseudocode Execution Improves Algorithmic Reasoning in Language Models
Paper • 2404.02575 • Published • 47 -
Toward Self-Improvement of LLMs via Imagination, Searching, and Criticizing
Paper • 2404.12253 • Published • 52 -
SnapKV: LLM Knows What You are Looking for Before Generation
Paper • 2404.14469 • Published • 23 -
FlowMind: Automatic Workflow Generation with LLMs
Paper • 2404.13050 • Published • 32