ReviewPatterns (New York, N.Y.)2025
Attention heads of large language models.
Review in Patterns (New York, N.Y.), 2025. The graph could read no effect estimate from its abstract, so it casts no vote on the map. Cited by 10 papers, 1 of them a synthesis that pooled it.
What it found
Each row is one number read from the abstract, on the scale the paper reported it, with its interval. Left of the dashed line favours the treatment, right favours the comparator. Under each row is the sentence it came from. New to these charts? A ten-minute tutorial.
The abstract states no effect estimate the extractor could read, or names no intervention and outcome on the map, so this paper lights no cell and moves no belief. It is still indexed, cited and linked below.
The trial behind it
Trials whose registry record cites this paper, or whose number appears in the abstract. A trial that started after this paper was published is citing it as background, not reporting it.
Neither the registry nor the abstract names a trial number. If this is a trial report, that itself is worth knowing.
Who cites it
10 citing papers in PubMed, 1 synthesis or guideline pooled it.
- Deep learning for MRI-based acute and subacute ischaemic stroke lesion segmentation-a systematic review, meta-analysis, and pilot evaluation of key results.Frontiers in medical technology · 2025Pooled it
- Iterative Development of an AI-Assisted Data Extraction Tool for Literature Synthesis in Oncology.Cureus · 2026Article
- AGCLD: an adaptive graph contrastive learning method with denoising for spatial domain identification.Briefings in bioinformatics · 2026Article
- Comparison of the performance of large language models in answering patient questions related to cataract.iScience · 2026Article
- Harnessing artificial intelligence for genomic variant prediction: advances, challenges, and future directions.GigaScience · 2026Review
- Artificial intelligence and robotic technologies redefining precision and personalization in orthopedic surgery: a narrative review.Frontiers in bioengineering and biotechnology · 2026Review
- Computational function prediction of bacteria and phage proteins.Microbiology and molecular biology reviews : MMBR · 2025Review
- Development and validation of large language model rating scales for automatically transcribed psychological therapy sessions.Scientific reports · 2025Article
- Artificial Intelligence in Orthopedic Surgery: Current Applications, Challenges, and Future Directions.MedComm · 2025Review
- Attention heads of large language models.Patterns (New York, N.Y.) · 2025Review
Corrections and comments
PubMed lists nothing against this paper. Absence here is not a guarantee, only a check that was made.
Authors and funding
8 authors.
Funding
No grant is acknowledged in the PubMed record.
Abstract
Large language models (LLMs) have demonstrated performance approaching human levels in tasks such as long-text comprehension and mathematical reasoning, but they remain black-box systems. Understanding the reasoning bottlenecks of LLMs remains a critical challenge, as these limitations are deeply tied to their internal architecture. Attention heads play a pivotal role in reasoning and are thought to share similarities with human brain functions. In this review, we explore the roles and mechanisms of attention heads to help demystify the internal reasoning processes of LLMs. We first introduce a four-stage framework inspired by the human thought process. Using this framework, we review existing research to identify and categorize the functions of specific attention heads. Additionally, we analyze the experimental methodologies used to discover these special heads and further summarize relevant evaluation methods and benchmarks. Finally, we discuss the limitations of current research and propose several potential future directions.
Indexed as
Identifiers
What OpenQuestion holds
Registered trials
Read under generation 80e0d062 · epoch 390. Bibliography from PubMed, PubMed Central and OpenAlex; grants from NIH RePORTER; trial links from ClinicalTrials.gov; estimates, votes and beliefs from the OpenQuestion graph.