Copertina

Linear Recency Bias During Training Improves Transformers' Fit to Reading Times

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Clark, Christian, Oh, Byung-Doh, Schuler, William
Natura:	Preprint
Pubblicazione:	2024
Soggetti:	Computation and Language
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Frequency Explains the Inverse Correlation of Large Language Models' Size, Training Data Amount, and Surprisal's Fit to Reading Times
di: Oh, Byung-Doh, et al.
Pubblicazione: (2024)

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

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

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

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

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

LayerNorm Induces Recency Bias in Transformer Decoders
di: Kim, Junu, et al.
Pubblicazione: (2025)

Citation Amnesia: On The Recency Bias of NLP and Other Academic Fields
di: Wahle, Jan Philip, et al.
Pubblicazione: (2024)

Vectors from Larger Language Models Predict Human Reading Time and fMRI Data More Poorly when Dimensionality Expansion is Controlled
di: Lin, Yi-Chien, et al.
Pubblicazione: (2025)

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

Emergence of Primacy and Recency Effect in Mamba: A Mechanistic Point of View
di: Airlangga, Muhammad Cendekia, et al.
Pubblicazione: (2025)

Big Tech-Funded AI Papers Have Higher Citation Impact, Greater Insularity, and Larger Recency Bias
di: Gnewuch, Max Martin, et al.
Pubblicazione: (2025)

How often do Answers Change? Estimating Recency Requirements in Question Answering
di: Piryani, Bhawna, et al.
Pubblicazione: (2026)

One-Topic-Doesn't-Fit-All: Transcreating Reading Comprehension Test for Personalized Learning
di: Han, Jieun, et al.
Pubblicazione: (2025)

Rethinking Test-Time Scaling for Medical AI: Model and Task-Aware Strategies for LLMs and VLMs
di: Oh, Gyutaek, et al.
Pubblicazione: (2025)

RoBIn: A Transformer-Based Model For Risk Of Bias Inference With Machine Reading Comprehension
di: Dias, Abel Corrêa, et al.
Pubblicazione: (2024)

Measuring Recency Bias In Sequential Recommendation Systems
di: Oh, Jeonglyul, et al.
Pubblicazione: (2024)

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

Experiments in News Bias Detection with Pre-Trained Neural Transformers
di: Menzner, Tim, et al.
Pubblicazione: (2024)

To Words and Beyond: Probing Large Language Models for Sentence-Level Psycholinguistic Norms of Memorability and Reading Times
di: Clark, Thomas Hikaru, et al.
Pubblicazione: (2026)

Gated Linear Attention Transformers with Hardware-Efficient Training
di: Yang, Songlin, et al.
Pubblicazione: (2023)

ModRWKV: Transformer Multimodality in Linear Time
di: Kang, Jiale, et al.
Pubblicazione: (2025)

Probing for Reading Times
di: Tsipidi, Eleftheria, et al.
Pubblicazione: (2026)

Fairness Dynamics During Training
di: Patel, Krishna, et al.
Pubblicazione: (2025)

No Training Wheels: Steering Vectors for Bias Correction at Inference Time
di: Gupta, Aviral, et al.
Pubblicazione: (2025)

Improving LLM Abilities in Idiomatic Translation
di: Donthi, Sundesh, et al.
Pubblicazione: (2024)

Transformer-VQ: Linear-Time Transformers via Vector Quantization
di: Lingle, Lucas D.
Pubblicazione: (2023)

The Effect of Surprisal on Reading Times in Information Seeking and Repeated Reading
di: Klein, Keren Gruteke, et al.
Pubblicazione: (2024)

Analyzing Bias in Swiss Federal Supreme Court Judgments Using Facebook's Holistic Bias Dataset: Implications for Language Model Training
di: Wehnert, Sabine, et al.
Pubblicazione: (2025)

AutoMedic: An Automated Evaluation Framework for Clinical Conversational Agents with Medical Dataset Grounding
di: Oh, Gyutaek, et al.
Pubblicazione: (2025)

Improved Models for Media Bias Detection and Subcategorization
di: Menzner, Tim, et al.
Pubblicazione: (2024)

Enhancing Training Data Attribution for Large Language Models with Fitting Error Consideration
di: Wu, Kangxi, et al.
Pubblicazione: (2024)

Bias A-head? Analyzing Bias in Transformer-Based Language Model Attention Heads
di: Yang, Yi, et al.
Pubblicazione: (2023)

Non-Linear Inference Time Intervention: Improving LLM Truthfulness
di: Hoscilowicz, Jakub, et al.
Pubblicazione: (2024)

Read Between the Lines: A Benchmark for Uncovering Political Bias in Bangla News Articles
di: Lia, Nusrat Jahan, et al.
Pubblicazione: (2025)

How Transformers Learn Regular Language Recognition: A Theoretical Study on Training Dynamics and Implicit Bias
di: Huang, Ruiquan, et al.
Pubblicazione: (2025)

Re-Reading Improves Reasoning in Large Language Models
di: Xu, Xiaohan, et al.
Pubblicazione: (2023)

Mitigating Length Bias in RLHF through a Causal Lens
di: Kim, Hyeonji, et al.
Pubblicazione: (2025)

Jump to Conclusions: Short-Cutting Transformers With Linear Transformations
di: Din, Alexander Yom, et al.
Pubblicazione: (2023)

Uncovering Factor Level Preferences to Improve Human-Model Alignment
di: Oh, Juhyun, et al.
Pubblicazione: (2024)