Token-Budget-Aware LLM Reasoning

arXiv:2412.18547 · cs.CL, cs.AI, cs.LG · Submitted 2024-12-24 · Read on arXiv

cs.CL, cs.AI, cs.LG

Submitted: 2024-12-24

Updated: 2026-10-16

Code: https://github.com/GeniusHTX/TALE

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Accuracy — 1× in this paper · explained in 1 episode
• Chain-of-Thought (CoT) — 1× in this paper · explained in 5 episodes
• Chain-of-Thought (CoT) Reasoning — 1× in this paper · explained in 4 episodes
• Large Language Models (LLMs) — 1× in this paper · explained in 8 episodes

Sources

• Program Synthesis with Large Language Models
• What's the Magic Word? A Control Theory of LLM Prompting
• PALM: Pre-training an Autoencoding&Autoregressive Language Model for Context-conditioned Generation
• Language Models are Hidden Reasoners: Unlocking Latent Reasoning Capabilities via Self-Rewarding
• Over-Reasoning and Redundant Calculation of Large Language Models
• Training Verifiers to Solve Math Word Problems
• The Llama 3 Herd of Models
• DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
• LLM Reasoners: New Evaluation, Library, and Analysis of Step-by-Step Reasoning with Large Language Models
• Reasoning with Language Model is Planning with World Model
• Training Large Language Models to Reason in a Continuous Latent Space
• Large Language Models Are Reasoning Teachers
• LoRA: Low-Rank Adaptation of Large Language Models
• CodeSearchNet Challenge: Evaluating the State of Semantic Code Search
• Exploring Concept Depth: How Large Language Models Acquire Knowledge and Concept at Different Layers?
• The Impact of Reasoning Step Length on Large Language Models
• MathBench: Evaluating the Theory and Application Proficiency of LLMs with a Hierarchical Mathematics Benchmark
• Faithful Chain-of-Thought Reasoning
• Concise Thoughts: Impact of Output Length on LLM Reasoning and Cost
• Visual Agents as Fast and Slow Thinkers

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering