Cover Image

Does Liking Yellow Imply Driving a School Bus? Semantic Leakage in Language Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Gonen, Hila, Blevins, Terra, Liu, Alisa, Zettlemoyer, Luke, Smith, Noah A.
Format:	Preprint
Published:	2024
Subjects:	Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Demystifying Prompts in Language Models via Perplexity Estimation
by: Gonen, Hila, et al.
Published: (2022)

MYTE: Morphology-Driven Byte Encoding for Better and Fairer Multilingual Language Modeling
by: Limisiewicz, Tomasz, et al.
Published: (2024)

Breaking the Curse of Multilinguality with Cross-lingual Expert Language Models
by: Blevins, Terra, et al.
Published: (2024)

Comparing Hallucination Detection Metrics for Multilingual Generation
by: Kang, Haoqiang, et al.
Published: (2024)

Accommodation Goes Both Ways: Studying Linguistic Convergence Between Humans and Language Models
by: Blevins, Terra
Published: (2026)

Rewriting History: A Recipe for Interventional Analyses to Study Data Effects on Model Behavior
by: Nadkarni, Rahul, et al.
Published: (2025)

Parameter Alignment Mitigates Catastrophic Forgetting in Multilingual Expert Language Models
by: Ahuja, Sanchit, et al.
Published: (2026)

Detecting Pretraining Data from Large Language Models
by: Shi, Weijia, et al.
Published: (2023)

OMNIGUARD: An Efficient Approach for AI Safety Moderation Across Languages and Modalities
by: Verma, Sahil, et al.
Published: (2025)

MAGNET: Improving the Multilingual Fairness of Language Models with Adaptive Gradient-Based Tokenization
by: Ahia, Orevaoghene, et al.
Published: (2024)

Sampling from Your Language Model One Byte at a Time
by: Hayase, Jonathan, et al.
Published: (2025)

Do language models accommodate their users? A study of linguistic convergence
by: Blevins, Terra, et al.
Published: (2025)

Voices Unheard: NLP Resources and Models for Yorùbá Regional Dialects
by: Ahia, Orevaoghene, et al.
Published: (2024)

Relation Extraction or Pattern Matching? Unravelling the Generalisation Limits of Language Models for Biographical RE
by: Arzt, Varvara, et al.
Published: (2025)

SILO Language Models: Isolating Legal Risk In a Nonparametric Datastore
by: Min, Sewon, et al.
Published: (2023)

Tuning Language Models by Proxy
by: Liu, Alisa, et al.
Published: (2024)

Universal NER v2: Towards a Massively Multilingual Named Entity Recognition Benchmark
by: Blevins, Terra, et al.
Published: (2026)

Universal NER: A Gold-Standard Multilingual Named Entity Recognition Benchmark
by: Mayhew, Stephen, et al.
Published: (2023)

Visual Sketchpad: Sketching as a Visual Chain of Thought for Multimodal Language Models
by: Hu, Yushi, et al.
Published: (2024)

Evaluating Copyright Takedown Methods for Language Models
by: Wei, Boyi, et al.
Published: (2024)

Calibration Is Not Enough: Evaluating Confidence Estimation Under Language Variations
by: Xia, Yuxi, et al.
Published: (2026)

Bolmo: Byteifying the Next Generation of Language Models
by: Minixhofer, Benjamin, et al.
Published: (2025)

Targeted Multilingual Adaptation for Low-resource Language Families
by: Downey, C. M., et al.
Published: (2024)

SuperBPE: Space Travel for Language Models
by: Liu, Alisa, et al.
Published: (2025)

Broken Tokens? Your Language Model can Secretly Handle Non-Canonical Tokenizations
by: Zheng, Brian Siyuan, et al.
Published: (2025)

MUSE: Machine Unlearning Six-Way Evaluation for Language Models
by: Shi, Weijia, et al.
Published: (2024)

Dementia Through Different Eyes: Explainable Modeling of Human and LLM Perceptions for Early Awareness
by: Peled-Cohen, Lotem, et al.
Published: (2025)

Correlation Does Not Imply Compensation: Complexity and Irregularity in the Lexicon
by: Doucette, Amanda, et al.
Published: (2024)

A Taxonomy of Ambiguity Types for NLP
by: Li, Margaret Y., et al.
Published: (2024)

Influence-driven Curriculum Learning for Pre-training on Limited Data
by: Schoenegger, Loris, et al.
Published: (2025)

Infini-gram: Scaling Unbounded n-gram Language Models to a Trillion Tokens
by: Liu, Jiacheng, et al.
Published: (2024)

Micro Language Models Enable Instant Responses
by: Cheng, Wen, et al.
Published: (2026)

Are you going to finish that? A Practical Study of the Partial Token Problem
by: Xu, Hao, et al.
Published: (2026)

Compute Optimal Tokenization
by: Limisiewicz, Tomasz, et al.
Published: (2026)

Scaling Down Semantic Leakage: Investigating Associative Bias in Smaller Language Models
by: Smilga, Veronika
Published: (2025)

Data Mixture Inference: What do BPE Tokenizers Reveal about their Training Data?
by: Hayase, Jonathan, et al.
Published: (2024)

Anchored Decoding: Provably Reducing Copyright Risk for Any Language Model
by: He, Jacqueline, et al.
Published: (2026)

Does a Large Language Model Really Speak in Human-Like Language?
by: Park, Mose, et al.
Published: (2025)

The Root Shapes the Fruit: On the Persistence of Gender-Exclusive Harms in Aligned Language Models
by: Ovalle, Anaelia, et al.
Published: (2024)

Assessing the Reliability of Large Language Models for Deductive Qualitative Coding: A Comparative Study of ChatGPT Interventions
by: Hila, Angjelin, et al.
Published: (2025)