Buchumschlag

Frequency Explains the Inverse Correlation of Large Language Models' Size, Training Data Amount, and Surprisal's Fit to Reading Times

Fuente: arXiv

Gespeichert in:

Bibliographische Detailangaben
Hauptverfasser:	Oh, Byung-Doh, Yue, Shisen, Schuler, William
Format:	Preprint
Veröffentlicht:	2024
Schlagworte:	Computation and Language Machine Learning
Online-Zugang:	Acceder al recurso
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Ähnliche Einträge

The Inverse Scaling Effect of Pre-Trained Language Model Surprisal Is Not Due to Data Leakage
von: Oh, Byung-Doh, et al.
Veröffentlicht: (2025)

The Impact of Token Granularity on the Predictive Power of Language Model Surprisal
von: Oh, Byung-Doh, et al.
Veröffentlicht: (2024)

Linear Recency Bias During Training Improves Transformers' Fit to Reading Times
von: Clark, Christian, et al.
Veröffentlicht: (2024)

Leading Whitespaces of Language Models' Subword Vocabulary Pose a Confound for Calculating Word Probabilities
von: Oh, Byung-Doh, et al.
Veröffentlicht: (2024)

Clozing the Gap: Exploring Why Language Model Surprisal Outperforms Cloze Surprisal
von: Nair, Sathvik, et al.
Veröffentlicht: (2026)

How Well Does First-Token Entropy Approximate Word Entropy as a Psycholinguistic Predictor?
von: Clark, Christian, et al.
Veröffentlicht: (2025)

Adaptive Pre-training Data Detection for Large Language Models via Surprising Tokens
von: Zhang, Anqi, et al.
Veröffentlicht: (2024)

SR-TTT: Surprisal-Aware Residual Test-Time Training
von: P, Swamynathan V
Veröffentlicht: (2026)

The Surprising Effectiveness of Test-Time Training for Few-Shot Learning
von: Akyürek, Ekin, et al.
Veröffentlicht: (2024)

Training Language Models to Explain Their Own Computations
von: Li, Belinda Z., et al.
Veröffentlicht: (2025)

Test-Time Training on Nearest Neighbors for Large Language Models
von: Hardt, Moritz, et al.
Veröffentlicht: (2023)

Explaining Large Language Models with gSMILE
von: Dehghani, Zeinab, et al.
Veröffentlicht: (2025)

Scaling Law for Language Models Training Considering Batch Size
von: Shuai, Xian, et al.
Veröffentlicht: (2024)

Large Language Models Are Latent Variable Models: Explaining and Finding Good Demonstrations for In-Context Learning
von: Wang, Xinyi, et al.
Veröffentlicht: (2023)

On The Truthfulness of 'Surprisingly Likely' Responses of Large Language Models
von: Goel, Naman
Veröffentlicht: (2023)

No One Size Fits All: QueryBandits for Hallucination Mitigation
von: Cho, Nicole, et al.
Veröffentlicht: (2026)

Surprisal from Larger Transformer-based Language Models Predicts fMRI Data More Poorly
von: Lin, Yi-Chien, et al.
Veröffentlicht: (2025)

Sequence-Level Leakage Risk of Training Data in Large Language Models
von: Tiwari, Trishita, et al.
Veröffentlicht: (2024)

Measuring Non-Adversarial Reproduction of Training Data in Large Language Models
von: Aerni, Michael, et al.
Veröffentlicht: (2024)

Inverse Reinforcement Learning Meets Large Language Model Post-Training: Basics, Advances, and Opportunities
von: Sun, Hao, et al.
Veröffentlicht: (2025)

JoPA:Explaining Large Language Model's Generation via Joint Prompt Attribution
von: Chang, Yurui, et al.
Veröffentlicht: (2024)

Regurgitative Training: The Value of Real Data in Training Large Language Models
von: Zhang, Jinghui, et al.
Veröffentlicht: (2024)

Explingo: Explaining AI Predictions using Large Language Models
von: Zytek, Alexandra, et al.
Veröffentlicht: (2024)

Explaining Large Language Models Decisions Using Shapley Values
von: Mohammadi, Behnam
Veröffentlicht: (2024)

DataFlex: A Unified Framework for Data-Centric Dynamic Training of Large Language Models
von: Liang, Hao, et al.
Veröffentlicht: (2026)

Cram Less to Fit More: Training Data Pruning Improves Memorization of Facts
von: Ye, Jiayuan, et al.
Veröffentlicht: (2026)

Detecting Training Data of Large Language Models via Expectation Maximization
von: Kim, Gyuwan, et al.
Veröffentlicht: (2024)

Exploring Cross-Client Memorization of Training Data in Large Language Models for Federated Learning
von: Udsa, Tinnakit, et al.
Veröffentlicht: (2025)

Explaining the role of Intrinsic Dimensionality in Adversarial Training
von: Altinisik, Enes, et al.
Veröffentlicht: (2024)

Federated Learning with Layer Skipping: Efficient Training of Large Language Models for Healthcare NLP
von: Zhang, Lihong, et al.
Veröffentlicht: (2025)

One Size Fits None: Heuristic Collapse in LLM Investment Advice
von: Ross, Jillian, et al.
Veröffentlicht: (2026)

Query-Conditioned Test-Time Self-Training for Large Language Models
von: Song, Chaehee, et al.
Veröffentlicht: (2026)

Min-K%++: Improved Baseline for Detecting Pre-Training Data from Large Language Models
von: Zhang, Jingyang, et al.
Veröffentlicht: (2024)

Comparative Performance Evaluation of Large Language Models for Extracting Molecular Interactions and Pathway Knowledge
von: Park, Gilchan, et al.
Veröffentlicht: (2023)

Escaping Collapse: The Strength of Weak Data for Large Language Model Training
von: Amin, Kareem, et al.
Veröffentlicht: (2025)

Fairness Definitions in Language Models Explained
von: Yin, Zhipeng, et al.
Veröffentlicht: (2024)

Self-Training Large Language Models with Confident Reasoning
von: Jang, Hyosoon, et al.
Veröffentlicht: (2025)

Linear Dynamics in the RLVR Training of Large Language Models
von: Wang, Tianle, et al.
Veröffentlicht: (2026)

Large Language Models as Interpolated and Extrapolated Event Predictors
von: Zhang, Libo, et al.
Veröffentlicht: (2024)

Explaining Graph Neural Networks with Large Language Models: A Counterfactual Perspective for Molecular Property Prediction
von: He, Yinhan, et al.
Veröffentlicht: (2024)