Copertina

ROME: Memorization Insights from Text, Logits and Representation

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Li, Bo, Zhao, Qinghua, Wen, Lijie
Natura:	Preprint
Pubblicazione:	2024
Soggetti:	Computation and Language Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Spectral Logit Sculpting: Adaptive Low-Rank Logit Transformation for Controlled Text Generation
di: Li, Jin, et al.
Pubblicazione: (2025)

Rebuilding ROME : Resolving Model Collapse during Sequential Model Editing
di: Gupta, Akshat, et al.
Pubblicazione: (2024)

Reassessing the Role of Chain-of-Thought in Sentiment Analysis: Insights and Limitations
di: Zheng, Kaiyuan, et al.
Pubblicazione: (2025)

Word Order's Impacts: Insights from Reordering and Generation Analysis
di: Zhao, Qinghua, et al.
Pubblicazione: (2024)

Let It Flow: Agentic Crafting on Rock and Roll, Building the ROME Model within an Open Agentic Learning Ecosystem
di: Wang, Weixun, et al.
Pubblicazione: (2025)

OWL: Probing Cross-Lingual Recall of Memorized Texts via World Literature
di: Srivastava, Alisha, et al.
Pubblicazione: (2025)

Memorization or Interpolation ? Detecting LLM Memorization through Input Perturbation Analysis
di: Djiré, Albérick Euraste, et al.
Pubblicazione: (2025)

Do LLMs Really Memorize Personally Identifiable Information? Revisiting PII Leakage with a Cue-Controlled Memorization Framework
di: Luo, Xiaoyu, et al.
Pubblicazione: (2026)

Arithmetic with Language Models: from Memorization to Computation
di: Maltoni, Davide, et al.
Pubblicazione: (2023)

Memorization in Attention-only Transformers
di: Dana, Léo, et al.
Pubblicazione: (2024)

FastMem: Fast Memorization of Prompt Improves Context Awareness of Large Language Models
di: Zhu, Junyi, et al.
Pubblicazione: (2024)

Data Compressibility Quantifies LLM Memorization
di: Huang, Yizhan, et al.
Pubblicazione: (2025)

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

ATLAS: Learning to Optimally Memorize the Context at Test Time
di: Behrouz, Ali, et al.
Pubblicazione: (2025)

Memorizing is Not Enough: Deep Knowledge Injection Through Reasoning
di: Xu, Ruoxi, et al.
Pubblicazione: (2025)

BiLD: Bi-directional Logits Difference Loss for Large Language Model Distillation
di: Li, Minchong, et al.
Pubblicazione: (2024)

A Training-Free Length Extrapolation Approach for LLMs: Greedy Attention Logit Interpolation (GALI)
di: Li, Yan, et al.
Pubblicazione: (2025)

DR-LoRA: Dynamic Rank LoRA for Fine-Tuning Mixture-of-Experts Models
di: Deng, Guanzhi, et al.
Pubblicazione: (2026)

Memorizing Documents with Guidance in Large Language Models
di: Park, Bumjin, et al.
Pubblicazione: (2024)

Memorization in Fine-Tuned Large Language Models
di: Savine, Danil
Pubblicazione: (2025)

Context Memorization for Efficient Long Context Generation
di: Okoshi, Yasuyuki, et al.
Pubblicazione: (2026)

Shared Path: Unraveling Memorization in Multilingual LLMs through Language Similarities
di: Luo, Xiaoyu, et al.
Pubblicazione: (2025)

Steering Language Models Before They Speak: Logit-Level Interventions
di: An, Hyeseon, et al.
Pubblicazione: (2026)

Logit Arithmetic Elicits Long Reasoning Capabilities Without Training
di: Zhang, Yunxiang, et al.
Pubblicazione: (2025)

TERGAD: Structure-Aware Text-Enhanced Representations for Graph Anomaly Detection
di: Shi, Wen, et al.
Pubblicazione: (2026)

DSIPA: Detecting LLM-Generated Texts via Sentiment-Invariant Patterns Divergence Analysis
di: Li, Siyuan, et al.
Pubblicazione: (2026)

Reversing the Forget-Retain Objectives: An Efficient LLM Unlearning Framework from Logit Difference
di: Ji, Jiabao, et al.
Pubblicazione: (2024)

Hierarchical Memorization in Large Language Models: Evidence from Citation Generation
di: Niimi, Junichiro
Pubblicazione: (2025)

Multiscale Positive-Unlabeled Detection of AI-Generated Texts
di: Tian, Yuchuan, et al.
Pubblicazione: (2023)

Diagnosing Memorization in Chain-of-Thought Reasoning, One Token at a Time
di: Li, Huihan, et al.
Pubblicazione: (2025)

LLMs Enable Bag-of-Texts Representations for Short-Text Clustering
di: Lin, I-Fan, et al.
Pubblicazione: (2025)

Undesirable Memorization in Large Language Models: A Survey
di: Satvaty, Ali, et al.
Pubblicazione: (2024)

Memorization in Large Language Models in Medicine: Prevalence, Characteristics, and Implications
di: Li, Anran, et al.
Pubblicazione: (2025)

Memorization in In-Context Learning
di: Golchin, Shahriar, et al.
Pubblicazione: (2024)

Learning to Compress: Unlocking the Potential of Large Language Models for Text Representation
di: Zhang, Yeqin, et al.
Pubblicazione: (2025)

Strategic Deflection: Defending LLMs from Logit Manipulation
di: Rachidy, Yassine, et al.
Pubblicazione: (2025)

Disentangling Preference Representation and Text Generation for Efficient Individual Preference Alignment
di: Zhang, Jianfei, et al.
Pubblicazione: (2024)

UNDIAL: Self-Distillation with Adjusted Logits for Robust Unlearning in Large Language Models
di: Dong, Yijiang River, et al.
Pubblicazione: (2024)

A Multi-Perspective Analysis of Memorization in Large Language Models
di: Chen, Bowen, et al.
Pubblicazione: (2024)

Recite, Reconstruct, Recollect: Memorization in LMs as a Multifaceted Phenomenon
di: Prashanth, USVSN Sai, et al.
Pubblicazione: (2024)