arXiv (All)
open access
Targeted Retrieval, Compact Representations: How CoT Reasoning Improves Long-Context Counting
Large language models (LLMs) have been rapidly improving in long-context tasks, powered by Chain-of-Thought (CoT) reasoning. However, the internal mechanisms underlying this improvement remain unclear. We investigate these mechanisms through a needle-in-a-haystack (NIAH) counting task, where an LLM
Conceptio Open Archive
Analyze & explore related research in Conceptio
Connect this record directly into your research workflow or AI agent. Explore citations across open repositories, query full text, and export structured proof bundles.
This document is indexed with metadata only: full text is not available in the archive for this record. Open the official source ↗
Related documents
- CWM: Controllable White-Box Meta-Prompting for Adaptive Retrieval-Augmented Generation and Reasoning Ability#1109276
- Why Thinking Hurts: Diagnosing and Rectifying Linguistic Inertia in Large Language Models for Recommendation#1129178
- A Recipe for Long-Context Reasoning in Large Language Models via On-Policy Optimization and Distillation#998226
- Choosing the Right Language Mode at Inference Time for Multilingual Reliability#927921
- Optimizing Large Language Models: Metrics, Energy Efficiency, and Case Study Insights#139146
Record · ID 1143925
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Bring this data into your agent: Connect via MCP or API · 20 free credits to start · no card required
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive