Cover Image

Not a nuisance but a useful heuristic: Outlier dimensions favor frequent tokens in language models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Macocco, Iuri, Graichen, Nora, Boleda, Gemma, Baroni, Marco
Format:	Preprint
Published:	2025
Subjects:	Computation and Language Artificial Intelligence I.2.7
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Prediction hubs are context-informed frequent tokens in LLMs
by: Nielsen, Beatrix M. G., et al.
Published: (2025)

Analyzing Large language models chatbots: An experimental approach using a probability test
by: Peruchini, Melise, et al.
Published: (2024)

Tracing Computation Density in LLMs
by: Kervadec, Corentin, et al.
Published: (2026)

Large-scale cloze evaluation reveals that token prediction tasks are neither lexically nor semantically aligned
by: Jacobs, Cassandra L., et al.
Published: (2024)

Unleashing the potential of prompt engineering for large language models
by: Chen, Banghao, et al.
Published: (2023)

Multilingual jailbreaking of LLMs using low-resource languages
by: Marx, Dylan, et al.
Published: (2026)

Plain language adaptations of biomedical text using LLMs: Comparision of evaluation metrics
by: Kocbek, Primoz, et al.
Published: (2025)

chDzDT: Word-level morphology-aware language model for Algerian social media text
by: Aries, Abdelkrime
Published: (2025)

Boundless Byte Pair Encoding: Breaking the Pre-tokenization Barrier
by: Schmidt, Craig W., et al.
Published: (2025)

RomanLens: The Role Of Latent Romanization In Multilinguality In LLMs
by: Saji, Alan, et al.
Published: (2025)

Text-Based Approaches to Item Difficulty Modeling in Large-Scale Assessments: A Systematic Review
by: Peters, Sydney, et al.
Published: (2025)

Classification of descriptions and summary using multiple passes of statistical and natural language toolkits
by: Banthia, Saumya, et al.
Published: (2020)

Low-Resource Court Judgment Summarization for Common Law Systems
by: Liu, Shuaiqi, et al.
Published: (2024)

Fine-Tuned 'Small' LLMs (Still) Significantly Outperform Zero-Shot Generative AI Models in Text Classification
by: Bucher, Martin Juan José, et al.
Published: (2024)

Evaluating the Efficacy of Hybrid Deep Learning Models in Distinguishing AI-Generated Text
by: Oketunji, Abiodun Finbarrs
Published: (2023)

Inference to the Best Explanation in Large Language Models
by: Dalal, Dhairya, et al.
Published: (2024)

Mechanistic evaluation of Transformers and state space models
by: Arora, Aryaman, et al.
Published: (2025)

Domain-specific ChatBots for Science using Embeddings
by: Yager, Kevin G.
Published: (2023)

Fine-tuning foundational models to code diagnoses from veterinary health records
by: Boguslav, Mayla R., et al.
Published: (2024)

Clinical information extraction for Low-resource languages with Few-shot learning using Pre-trained language models and Prompting
by: Richter-Pechanski, Phillip, et al.
Published: (2024)

Enhancing Long-Term Memory using Hierarchical Aggregate Tree for Retrieval Augmented Generation
by: A, Aadharsh Aadhithya, et al.
Published: (2024)

Machine Translation Hallucination Detection for Low and High Resource Languages using Large Language Models
by: Benkirane, Kenza, et al.
Published: (2024)

NinjaLLM: Fast, Scalable and Cost-effective RAG using Amazon SageMaker and AWS Trainium and Inferentia2
by: Xue, Tengfei, et al.
Published: (2024)

Neural Machine Translation for Malayalam Paraphrase Generation
by: Varghese, Christeena, et al.
Published: (2024)

Is Our Chatbot Telling Lies? Assessing Correctness of an LLM-based Dutch Support Chatbot
by: Lassche, Herman, et al.
Published: (2024)

Predictive Simultaneous Interpretation: Harnessing Large Language Models for Democratizing Real-Time Multilingual Communication
by: Iida, Kurando, et al.
Published: (2024)

Exploring RWKV for Sentence Embeddings: Layer-wise Analysis and Baseline Comparison for Semantic Similarity
by: Pan, Xinghan
Published: (2025)

UA-Legal-Bench: A Benchmark for Evaluating Large Language Models on Ukrainian Legal Reasoning
by: Ovcharov, Volodymyr
Published: (2026)

Option-Order Randomisation Reveals a Distributional Position Attractor in Prompted Sandbagging
by: Cacioli, Jon-Paul
Published: (2026)

Sticker-TTS: Learn to Utilize Historical Experience with a Sticker-driven Test-Time Scaling Framework
by: Chen, Jie, et al.
Published: (2025)

Exploring News Summarization and Enrichment in a Highly Resource-Scarce Indian Language: A Case Study of Mizo
by: Bala, Abhinaba, et al.
Published: (2024)

Exploiting LLM-as-a-Judge Disposition on Free Text Legal QA via Prompt Optimization
by: Elganayni, Mohamed Hesham, et al.
Published: (2026)

Robustness of Large Language Models to Perturbations in Text
by: Singh, Ayush, et al.
Published: (2024)

Evaluating Class Membership Relations in Knowledge Graphs using Large Language Models
by: Allen, Bradley P., et al.
Published: (2024)

Large Language Model (LLM) Bias Index -- LLMBI
by: Oketunji, Abiodun Finbarrs, et al.
Published: (2023)

KAConvText: Novel Approach to Burmese Sentence Classification using Kolmogorov-Arnold Convolution
by: Thu, Ye Kyaw, et al.
Published: (2025)

UrduBench: An Urdu Reasoning Benchmark using Contextually Ensembled Translations with Human-in-the-Loop
by: Shafique, Muhammad Ali, et al.
Published: (2026)

Beyond Prefixes: Graph-as-Memory Cross-Attention for Knowledge Graph Completion with Large Language Models
by: Liu, Ruitong, et al.
Published: (2025)

LLMs as Signal Detectors: Sensitivity, Bias, and the Temperature-Criterion Analogy
by: Cacioli, Jon-Paul
Published: (2026)

The Dual-Route Model of Induction
by: Feucht, Sheridan, et al.
Published: (2025)