Can Large Language Models Understand Context?
Paper
•
2402.00858
•
Published
•
21
reasoning
-
-
Efficient Tool Use with Chain-of-Abstraction Reasoning
Paper • 2401.17464 • Published • 16 -
ReFT: Reasoning with Reinforced Fine-Tuning
Paper • 2401.08967 • Published • 29 -
The Impact of Reasoning Step Length on Large Language Models
Paper • 2401.04925 • Published • 16 -
Chain-of-Table: Evolving Tables in the Reasoning Chain for Table Understanding
Paper • 2401.04398 • Published • 21 -
Self-Discover: Large Language Models Self-Compose Reasoning Structures
Paper • 2402.03620 • Published • 112 -
Bias Runs Deep: Implicit Reasoning Biases in Persona-Assigned LLMs
Paper • 2311.04892 • Published • 1 -
More Agents Is All You Need
Paper • 2402.05120 • Published • 51 -
Grandmaster-Level Chess Without Search
Paper • 2402.04494 • Published • 67 -
The Benefits of a Concise Chain of Thought on Problem-Solving in Large Language Models
Paper • 2401.05618 • Published • 1 -
Divide-or-Conquer? Which Part Should You Distill Your LLM?
Paper • 2402.15000 • Published • 22 -
System 2 Attention (is something you might need too)
Paper • 2311.11829 • Published • 39 -
Quiet-STaR: Language Models Can Teach Themselves to Think Before Speaking
Paper • 2403.09629 • Published • 74 -
On the Conversational Persuasiveness of Large Language Models: A Randomized Controlled Trial
Paper • 2403.14380 • Published • 1 -
Orca-Math: Unlocking the potential of SLMs in Grade School Math
Paper • 2402.14830 • Published • 24 -
Language Models as Compilers: Simulating Pseudocode Execution Improves Algorithmic Reasoning in Language Models
Paper • 2404.02575 • Published • 48 -
Compression Represents Intelligence Linearly
Paper • 2404.09937 • Published • 27 -
Democratizing Reasoning Ability: Tailored Learning from Large Language Model
Paper • 2310.13332 • Published • 14 -
DeepSeek-Prover: Advancing Theorem Proving in LLMs through Large-Scale Synthetic Data
Paper • 2405.14333 • Published • 36 -
Large Language Models as Planning Domain Generators
Paper • 2405.06650 • Published • 9 -
ALPINE: Unveiling the Planning Capability of Autoregressive Learning in Language Models
Paper • 2405.09220 • Published • 24 -
On the Brittle Foundations of ReAct Prompting for Agentic Large Language Models
Paper • 2405.13966 • Published -
Grokked Transformers are Implicit Reasoners: A Mechanistic Journey to the Edge of Generalization
Paper • 2405.15071 • Published • 37 -
Accessing GPT-4 level Mathematical Olympiad Solutions via Monte Carlo Tree Self-refine with LLaMa-3 8B
Paper • 2406.07394 • Published • 24 -
Mixture-of-Agents Enhances Large Language Model Capabilities
Paper • 2406.04692 • Published • 55 -
Your Context Is Not an Array: Unveiling Random Access Limitations in Transformers
Paper • 2408.05506 • Published • 8 -
Mutual Reasoning Makes Smaller LLMs Stronger Problem-Solvers
Paper • 2408.06195 • Published • 63