Imagen de Portada

Next Token Knowledge Tracing: Exploiting Pretrained LLM Representations to Decode Student Behaviour

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Norris, Max, Gal, Kobi, Bulathwela, Sahan
Formato:	Preprint
Publicado:	2025
Materias:	Computation and Language Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Catching The Correct Answer Trap: Characterising AI Tutor Blind Spots When Analysing Student Reasoning
por: Imran, Moiz, et al.
Publicado: (2026)

Exploring Human-AI Complementarity in CPS Diagnosis Using Unimodal and Multimodal BERT Models
por: Wong, Kester, et al.
Publicado: (2025)

Explainable Collaborative Problem Solving Diagnosis with BERT using SHAP and its Implications for Teacher Adoption
por: Wong, Kester, et al.
Publicado: (2025)

Stereotype Detection in LLMs: A Multiclass, Explainable, and Benchmark-Driven Approach
por: Wu, Zekun, et al.
Publicado: (2024)

Mix and Match: Context Pairing for Scalable Topic-Controlled Educational Summarisation
por: Yodthapa, Nathikan, et al.
Publicado: (2026)

A Novel Approach to Scalable and Automatic Topic-Controlled Question Generation in Education
por: Li, Ziqing, et al.
Publicado: (2025)

Tracing Persona Vectors Through LLM Pretraining
por: Moskvoretskii, Viktor, et al.
Publicado: (2026)

The Knowledge-Behaviour Disconnect in LLM-based Chatbots
por: Broersen, Jan
Publicado: (2025)

LFD: Layer Fused Decoding to Exploit External Knowledge in Retrieval-Augmented Generation
por: Sun, Yang, et al.
Publicado: (2025)

LLM-Oriented Token-Adaptive Knowledge Distillation
por: Xie, Xurong, et al.
Publicado: (2025)

The Tokenization Bottleneck: How Vocabulary Extension Improves Chemistry Representation Learning in Pretrained Language Models
por: Kalamkar, Prathamesh, et al.
Publicado: (2025)

Next Token Perception Score: Analytical Assessment of your LLM Perception Skills
por: Cheng, Yu-Ang, et al.
Publicado: (2025)

Rep2Text: Decoding Full Text from a Single LLM Token Representation
por: Zhao, Haiyan, et al.
Publicado: (2025)

Tracing the Representation Geometry of Language Models from Pretraining to Post-training
por: Li, Melody Zixuan, et al.
Publicado: (2025)

Interpretable Difficulty-Aware Knowledge Tracing in Tutor-Student Dialogues
por: Huang, Shuyan, et al.
Publicado: (2026)

Towards Synergistic Teacher-AI Interactions with Generative Artificial Intelligence
por: Cukurova, Mutlu, et al.
Publicado: (2025)

Tool Calling is Linearly Readable and Steerable in Language Models
por: Wu, Zekun, et al.
Publicado: (2026)

Examining Student Interactions with a Pedagogical AI-Assistant for Essay Writing and their Impact on Students Writing Quality
por: Febriantoro, Wicaksono, et al.
Publicado: (2025)

LLMs are Not Just Next Token Predictors
por: Downes, Stephen M., et al.
Publicado: (2024)

Direct Multi-Token Decoding
por: Luo, Xuan, et al.
Publicado: (2025)

Do We Need Distinct Representations for Every Speech Token? Unveiling and Exploiting Redundancy in Large Speech Language Models
por: Xiang, Bajian, et al.
Publicado: (2026)

Next-Token Prediction Task Assumes Optimal Data Ordering for LLM Training in Proof Generation
por: An, Chenyang, et al.
Publicado: (2024)

Not All Options Are Created Equal: Textual Option Weighting for Token-Efficient LLM-Based Knowledge Tracing
por: Kim, JongWoo, et al.
Publicado: (2024)

Beyond Behavioural Trade-Offs: Mechanistic Tracing of Pain-Pleasure Decisions in an LLM
por: Bianco, Francesca, et al.
Publicado: (2026)

Rethinking the Potential of Multimodality in Collaborative Problem Solving Diagnosis with Large Language Models
por: Wong, K., et al.
Publicado: (2025)

IGOT: Information Gain Optimized Tokenizer on Domain Adaptive Pretraining
por: Feng, Dawei, et al.
Publicado: (2024)

From Next-Token to Next-Block: A Principled Adaptation Path for Diffusion LLMs
por: Tian, Yuchuan, et al.
Publicado: (2025)

Behavior-Aware Item Modeling via Dynamic Procedural Solution Representations for Knowledge Tracing
por: Seo, Jun, et al.
Publicado: (2026)

PLDR-LLM: Large Language Model from Power Law Decoder Representations
por: Gokden, Burc
Publicado: (2024)

Knowledgeable In-Context Tuning: Exploring and Exploiting Factual Knowledge for In-Context Learning
por: Wang, Jianing, et al.
Publicado: (2023)

Cautious Next Token Prediction
por: Wang, Yizhou, et al.
Publicado: (2025)

Token-Guard: Towards Token-Level Hallucination Control via Self-Checking Decoding
por: Zhu, Yifan, et al.
Publicado: (2026)

Alternatives To Next Token Prediction In Text Generation -- A Survey
por: Wyatt, Charlie, et al.
Publicado: (2025)

TPA: Next Token Probability Attribution for Detecting Hallucinations in RAG
por: Lu, Pengqian, et al.
Publicado: (2025)

Fractal Patterns May Illuminate the Success of Next-Token Prediction
por: Alabdulmohsin, Ibrahim, et al.
Publicado: (2024)

CreditDecoding: Accelerating Parallel Decoding in Diffusion Large Language Models with Trace Credit
por: Wang, Kangyu, et al.
Publicado: (2025)

Uncovering Autoregressive LLM Knowledge of Thematic Fit in Event Representation
por: Alshemali, Safeyah Khaled, et al.
Publicado: (2024)

GRIFFIN: Effective Token Alignment for Faster Speculative Decoding
por: Hu, Shijing, et al.
Publicado: (2025)

Reflection Pretraining Enables Token-Level Self-Correction in Biological Sequence Models
por: Zhang, Xiang, et al.
Publicado: (2025)

On Linear Representations and Pretraining Data Frequency in Language Models
por: Merullo, Jack, et al.
Publicado: (2025)