Image de couverture de livre

Is my model "mind blurting"? Interpreting the dynamics of reasoning tokens with Recurrence Quantification Analysis (RQA)

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Pham, Quoc Tuan, Jafari, Mehdi, Salim, Flora
Format:	Preprint
Publié:	2026
Sujets:	Computation and Language
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Mechanistic Indicators of Steering Effectiveness in Large Language Models
par: Jafari, Mehdi, et autres
Publié: (2026)

Enhancing Conversational Agents with Theory of Mind: Aligning Beliefs, Desires, and Intentions for Human-Like Interaction
par: Jafari, Mehdi, et autres
Publié: (2025)

PyRQA -- Conducting Recurrence Quantification Analysis on Very Long Time Series Efficiently
par: Rawald, Tobias, et autres
Publié: (2024)

Is my model perplexed for the right reason? Contrasting LLMs' Benchmark Behavior with Token-Level Perplexity
par: Prins, Zoë, et autres
Publié: (2026)

Interpreting token compositionality in LLMs: A robustness analysis
par: Aljaafari, Nura, et autres
Publié: (2024)

LocalRQA: From Generating Data to Locally Training, Testing, and Deploying Retrieval-Augmented QA Systems
par: Yu, Xiao, et autres
Publié: (2024)

ClozeMath: Improving Mathematical Reasoning in Language Models by Learning to Fill Equations
par: Pham, Quang Hieu, et autres
Publié: (2025)

What am I missing here?: Evaluating Large Language Models for Masked Sentence Prediction
par: Wyatt, Charlie, et autres
Publié: (2025)

Contextual morphologically-guided tokenization for Latin encoder models
par: Hudspeth, Marisa, et autres
Publié: (2025)

Harnessing Test-time Adaptation for NLU tasks Involving Dialects of English
par: Nguyen, Duke, et autres
Publié: (2025)

Alternatives To Next Token Prediction In Text Generation -- A Survey
par: Wyatt, Charlie, et autres
Publié: (2025)

Interpretable Next-token Prediction via the Generalized Induction Head
par: Kim, Eunji, et autres
Publié: (2024)

Explore Theory of Mind: Program-guided adversarial data generation for theory of mind reasoning
par: Sclar, Melanie, et autres
Publié: (2024)

Towards Reliable Medical Question Answering: Techniques and Challenges in Mitigating Hallucinations in Language Models
par: Pham, Duy Khoa, et autres
Publié: (2024)

Who's Who: Large Language Models Meet Knowledge Conflicts in Practice
par: Pham, Quang Hieu, et autres
Publié: (2024)

Collaborative decoding of critical tokens for boosting factuality of large language models
par: Jin, Lifeng, et autres
Publié: (2024)

MAPLE: Mobile App Prediction Leveraging Large Language Model Embeddings
par: Khaokaew, Yonchanok, et autres
Publié: (2023)

Do language models plan ahead for future tokens?
par: Wu, Wilson, et autres
Publié: (2024)

Visualizing token importance for black-box language models
par: Rauba, Paulius, et autres
Publié: (2025)

Mitigating Data Scarcity in Psychological Defense Classification with Context-Aware Synthetic Augmentation
par: Vu, Hoang-Thuy-Duong, et autres
Publié: (2026)

On the scaling relationship between cloze probabilities and language model next-token prediction
par: Jacobs, Cassandra L., et autres
Publié: (2026)

PERCORE: A Deep Learning-Based Framework for Persian Spelling Correction with Phonetic Analysis
par: Dashti, Seyed Mohammad Sadegh, et autres
Publié: (2024)

Distributional reasoning in LLMs: Parallel reasoning processes in multi-hop reasoning
par: Shalev, Yuval, et autres
Publié: (2024)

Revisiting subword tokenization: A case study on affixal negation in large language models
par: Truong, Thinh Hung, et autres
Publié: (2024)

Practical token pruning for foundation models in few-shot conversational virtual assistant systems
par: Qi, Haode, et autres
Publié: (2024)

Why do LLMs attend to the first token?
par: Barbero, Federico, et autres
Publié: (2025)

Where is the signal in tokenization space?
par: Geh, Renato Lui, et autres
Publié: (2024)

Leveraging Sentence-oriented Augmentation and Transformer-Based Architecture for Vietnamese-Bahnaric Translation
par: Nguyen, Tan Sang, et autres
Publié: (2026)

On the token distance modeling ability of higher RoPE attention dimension
par: Hong, Xiangyu, et autres
Publié: (2024)

Byte-token Enhanced Language Models for Temporal Point Processes Analysis
par: Kong, Quyu, et autres
Publié: (2025)

ZARA: Training-Free Motion Time-Series Reasoning via Evidence-Grounded LLM Agents
par: Li, Zechen, et autres
Publié: (2025)

CP-MoE: Consistency-Preserving Mixture-of-Experts for Continual Learning
par: Liu, Yang, et autres
Publié: (2026)

SensorLLM: Aligning Large Language Models with Motion Sensors for Human Activity Recognition
par: Li, Zechen, et autres
Publié: (2024)

Prompt Mining for Language-based Human Mobility Forecasting
par: Xue, Hao, et autres
Publié: (2024)

World model inspired sarcasm reasoning with large language model agents
par: Inoshita, Keito, et autres
Publié: (2025)

Comparative analysis of subword tokenization approaches for Indian languages
par: Das, Sudhansu Bala, et autres
Publié: (2025)

Automatic Real-word Error Correction in Persian Text
par: Dashti, Seyed Mohammad Sadegh, et autres
Publié: (2024)

Language models are better than humans at next-token prediction
par: Shlegeris, Buck, et autres
Publié: (2022)

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

Retrieval-augmented reasoning with lean language models
par: Chan, Ryan Sze-Yin, et autres
Publié: (2025)