Cover Image

Interpreting token compositionality in LLMs: A robustness analysis

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Aljaafari, Nura, Carvalho, Danilo S., Freitas, André
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

The Mechanics of Conceptual Interpretation in GPT Models: Interpretative Insights
by: Aljaafari, Nura, et al.
Published: (2024)

TRACE: Training and Inference-Time Interpretability Analysis for Language Models
by: Aljaafari, Nura, et al.
Published: (2025)

Emergence and Localisation of Semantic Role Circuits in LLMs
by: Aljaafari, Nura, et al.
Published: (2025)

CARMA: Enhanced Compositionality in LLMs via Advanced Regularisation and Mutual Information Alignment
by: Aljaafari, Nura, et al.
Published: (2025)

TRACE for Tracking the Emergence of Semantic Representations in Transformers
by: Aljaafari, Nura, et al.
Published: (2025)

Is Inference Mediated by Distinct Semantic Structures in LLMs? A Mechanistic Interpretation
by: Aljaafari, Nura, et al.
Published: (2026)

From Circuit Evidence to Mechanistic Theory: An Inductive Logic Approach
by: Aljaafari, Nura, et al.
Published: (2026)

Bridging Compositional and Distributional Semantics: A Survey on Latent Semantic Geometry via AutoEncoder
by: Zhang, Yingji, et al.
Published: (2025)

Inductive Learning of Logical Theories with LLMs: An Expressivity-Graded Analysis
by: Gandarela, João Pedro, et al.
Published: (2024)

Quasi-symbolic Semantic Geometry over Transformer-based Variational AutoEncoder
by: Zhang, Yingji, et al.
Published: (2022)

Learning Disentangled Semantic Spaces of Explanations via Invertible Neural Networks
by: Zhang, Yingji, et al.
Published: (2023)

Multi-Relational Hyperbolic Word Embeddings from Natural Language Definitions
by: Valentino, Marco, et al.
Published: (2023)

Learning to Disentangle Latent Reasoning Rules with Language VAEs: A Systematic Study
by: Zhang, Yingji, et al.
Published: (2025)

Why do LLMs attend to the first token?
by: Barbero, Federico, et al.
Published: (2025)

Towards Controllable Natural Language Inference through Lexical Inference Types
by: Zhang, Yingji, et al.
Published: (2023)

LangVAE and LangSpace: Building and Probing for Language Model VAEs
by: Carvalho, Danilo S., et al.
Published: (2025)

SylloBio-NLI: Evaluating Large Language Models on Biomedical Syllogistic Reasoning
by: Wysocka, Magdalena, et al.
Published: (2024)

Montague semantics and modifier consistency measurement in neural language models
by: Carvalho, Danilo S., et al.
Published: (2022)

AnomaLLMy -- Detecting anomalous tokens in black-box LLMs through low-confidence single-token predictions
by: Witold, Waligóra
Published: (2024)

Tokenization counts: the impact of tokenization on arithmetic in frontier LLMs
by: Singh, Aaditya K., et al.
Published: (2024)

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

Jacobian Scopes: token-level causal attributions in LLMs
by: Liu, Toni J. B., et al.
Published: (2026)

Finetuning LLMs for EvaCun 2025 token prediction shared task
by: Jon, Josef, et al.
Published: (2025)

Comparative analysis of subword tokenization approaches for Indian languages
by: Das, Sudhansu Bala, et al.
Published: (2025)

Improving Semantic Control in Discrete Latent Spaces with Transformer Quantized Variational Autoencoders
by: Zhang, Yingji, et al.
Published: (2024)

PEIRCE: Unifying Material and Formal Reasoning via LLM-Driven Neuro-Symbolic Refinement
by: Quan, Xin, et al.
Published: (2025)

Interpretable Next-token Prediction via the Generalized Induction Head
by: Kim, Eunji, et al.
Published: (2024)

Is my model "mind blurting"? Interpreting the dynamics of reasoning tokens with Recurrence Quantification Analysis (RQA)
by: Pham, Quoc Tuan, et al.
Published: (2026)

Accelerating Antibiotic Discovery with Large Language Models and Knowledge Graphs
by: Delmas, Maxime, et al.
Published: (2025)

Autoformalization in the Wild: Assessing LLMs on Real-World Mathematical Definitions
by: Zhang, Lan, et al.
Published: (2025)

Towards Nepali-language LLMs: Efficient GPT training with a Nepali BPE tokenizer
by: Shrestha, Adarsha, et al.
Published: (2025)

Where is the signal in tokenization space?
by: Geh, Renato Lui, et al.
Published: (2024)

Reasoning Circuits in Language Models: A Mechanistic Interpretation of Syllogistic Inference
by: Kim, Geonhee, et al.
Published: (2024)

Contextual morphologically-guided tokenization for Latin encoder models
by: Hudspeth, Marisa, et al.
Published: (2025)

You only need 4 extra tokens: Synergistic Test-time Adaptation for LLMs
by: Xu, Yijie, et al.
Published: (2025)

DeepMLF: Multimodal language model with learnable tokens for deep fusion in sentiment analysis
by: Georgiou, Efthymios, et al.
Published: (2025)

The pitfalls of next-token prediction
by: Bachmann, Gregor, et al.
Published: (2024)

Looking beyond the next token
by: Thankaraj, Abitha, et al.
Published: (2025)

On multi-token prediction for efficient LLM inference
by: Mehra, Somesh, et al.
Published: (2025)

A Survey in Mathematical Language Processing
by: Meadows, Jordan, et al.
Published: (2022)