Cover Image

Positional Fragility in LLMs: How Offset Effects Reshape Our Understanding of Memorization Risks

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Xu, Yixuan, Llaquet, Antoni-Joan Solergibert i, Bosselut, Antoine, Schlag, Imanol
Format:	Preprint
Published:	2025
Subjects:	Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Can Performant LLMs Be Ethical? Quantifying the Impact of Web Crawling Opt-Outs
by: Fan, Dongyang, et al.
Published: (2025)

Benchmarking Concept-Spilling Across Languages in LLMs
by: Badanin, Ilia, et al.
Published: (2026)

On the Effect of (Near) Duplicate Subwords in Language Modelling
by: Schäfer, Anton, et al.
Published: (2024)

From Language to Cognition: How LLMs Outgrow the Human Language Network
by: AlKhamissi, Badr, et al.
Published: (2025)

Tracking the Limits of Knowledge Propagation: How LLMs Fail at Multi-Step Reasoning with Conflicting Knowledge
by: Feng, Yiyang, et al.
Published: (2026)

Memorization or Reasoning? Exploring the Idiom Understanding of LLMs
by: Kim, Jisu, et al.
Published: (2025)

AbstRaL: Augmenting LLMs' Reasoning by Reinforcing Abstract Thinking
by: Gao, Silin, et al.
Published: (2025)

LLMs Are In-Context Bandit Reinforcement Learners
by: Monea, Giovanni, et al.
Published: (2024)

Understanding Verbatim Memorization in LLMs Through Circuit Discovery
by: Lasy, Ilya, et al.
Published: (2025)

Spurious Rewards Paradox: Mechanistically Understanding How RLVR Activates Memorization Shortcuts in LLMs
by: Yan, Lecheng, et al.
Published: (2026)

Instruction-tuning Aligns LLMs to the Human Brain
by: Aw, Khai Loong, et al.
Published: (2023)

Do LLMs Game Formalization? Evaluating Faithfulness in Logical Reasoning
by: Kim, Kyuhee, et al.
Published: (2026)

SFT-then-RL Outperforms Mixed-Policy Methods for LLM Reasoning
by: Limozin, Alexis, et al.
Published: (2026)

RLMEval: Evaluating Research-Level Neural Theorem Proving
by: Poiroux, Auguste, et al.
Published: (2025)

The Role of Language Imbalance in Cross-lingual Generalisation: Insights from Cloned Language Experiments
by: Schäfer, Anton, et al.
Published: (2024)

JOBSKAPE: A Framework for Generating Synthetic Job Postings to Enhance Skill Matching
by: Magron, Antoine, et al.
Published: (2024)

How Robust Are Router-LLMs? Analysis of the Fragility of LLM Routing Capabilities
by: Kassem, Aly M., et al.
Published: (2025)

Memorization and Knowledge Injection in Gated LLMs
by: Pan, Xu, et al.
Published: (2025)

How LLMs Distort Our Written Language
by: Abdulhai, Marwa, et al.
Published: (2026)

Be like a Goldfish, Don't Memorize! Mitigating Memorization in Generative LLMs
by: Hans, Abhimanyu, et al.
Published: (2024)

Let Me Teach You: Pedagogical Foundations of Feedback for Language Models
by: Borges, Beatriz, et al.
Published: (2023)

Making Reasoning Matter: Measuring and Improving Faithfulness of Chain-of-Thought Reasoning
by: Paul, Debjit, et al.
Published: (2024)

Crosscoding Through Time: Tracking Emergence & Consolidation Of Linguistic Representations Throughout LLM Pretraining
by: Bayazit, Deniz, et al.
Published: (2025)

Quantifying In-Context Reasoning Effects and Memorization Effects in LLMs
by: Lou, Siyu, et al.
Published: (2024)

An Engineering Journey Training Large Language Models at Scale on Alps: The Apertus Experience
by: Coles, Jonathan, et al.
Published: (2026)

Rethinking Skill Extraction in the Job Market Domain using Large Language Models
by: Nguyen, Khanh Cao, et al.
Published: (2024)

MedMT-Bench: Can LLMs Memorize and Understand Long Multi-Turn Conversations in Medical Scenarios?
by: Yang, Lin, et al.
Published: (2026)

Long-Term Ad Memorability: Understanding & Generating Memorable Ads
by: SI, Harini, et al.
Published: (2023)

Alpaca against Vicuna: Using LLMs to Uncover Memorization of LLMs
by: Kassem, Aly M., et al.
Published: (2024)

PERK: Long-Context Reasoning as Parameter-Efficient Test-Time Learning
by: Chen, Zeming, et al.
Published: (2025)

Complex Reasoning over Logical Queries on Commonsense Knowledge Graphs
by: Fang, Tianqing, et al.
Published: (2024)

PICLe: Pseudo-Annotations for In-Context Learning in Low-Resource Named Entity Detection
by: Mamooler, Sepideh, et al.
Published: (2024)

Mitigating Memorization in LLMs using Activation Steering
by: Suri, Manan, et al.
Published: (2025)

How Value Induction Reshapes LLM Behaviour
by: Arora, Arnav, et al.
Published: (2026)

Edited Media Understanding Frames: Reasoning About the Intent and Implications of Visual Misinformation
by: Da, Jeff, et al.
Published: (2020)

Deriving Activation Functions Using Integration
by: Huang, Allen Hao, et al.
Published: (2024)

Unveiling Over-Memorization in Finetuning LLMs for Reasoning Tasks
by: Ruan, Zhiwen, et al.
Published: (2025)

The LLM Language Network: A Neuroscientific Approach for Identifying Causally Task-Relevant Units
by: AlKhamissi, Badr, et al.
Published: (2024)

Brain-Like Language Processing via a Shallow Untrained Multihead Attention Network
by: AlKhamissi, Badr, et al.
Published: (2024)

Position: Privacy Is Not Just Memorization!
by: Mireshghallah, Niloofar, et al.
Published: (2025)