Image de couverture de livre

Mirage of Mastery: Memorization Tricks LLMs into Artificially Inflated Self-Knowledge

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteur principal:	Kale, Sahil
Format:	Preprint
Publié:	2025
Sujets:	Computation and Language
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Lie to Me: Knowledge Graphs for Robust Hallucination Self-Detection in LLMs
par: Kale, Sahil, et autres
Publié: (2025)

Look It Up: Analysing Internal Web Search Capabilities of Modern LLMs
par: Kale, Sahil
Publié: (2025)

Line of Duty: Evaluating LLM Self-Knowledge via Consistency in Feasibility Boundaries
par: Kale, Sahil, et autres
Publié: (2025)

TeXpert: A Multi-Level Benchmark for Evaluating LaTeX Code Generation by LLMs
par: Kale, Sahil, et autres
Publié: (2025)

Memorization and Knowledge Injection in Gated LLMs
par: Pan, Xu, et autres
Publié: (2025)

LLM Self Defense: By Self Examination, LLMs Know They Are Being Tricked
par: Phute, Mansi, et autres
Publié: (2023)

FAQ-Gen: An automated system to generate domain-specific FAQs to aid content comprehension
par: Kale, Sahil, et autres
Publié: (2024)

KnowRL: Teaching Language Models to Know What They Know
par: Kale, Sahil, et autres
Publié: (2025)

Tricking LLMs into Disobedience: Formalizing, Analyzing, and Detecting Jailbreaks
par: Rao, Abhinav, et autres
Publié: (2023)

From Exploration to Mastery: Enabling LLMs to Master Tools via Self-Driven Interactions
par: Qu, Changle, et autres
Publié: (2024)

LLMs as Narcissistic Evaluators: When Ego Inflates Evaluation Scores
par: Liu, Yiqi, et autres
Publié: (2023)

Memorization vs. Reasoning: Updating LLMs with New Knowledge
par: Li, Aochong Oliver, et autres
Publié: (2025)

Be like a Goldfish, Don't Memorize! Mitigating Memorization in Generative LLMs
par: Hans, Abhimanyu, et autres
Publié: (2024)

Wired for Overconfidence: A Mechanistic Perspective on Inflated Verbalized Confidence in LLMs
par: Zhao, Tianyi, et autres
Publié: (2026)

Skywork-Reward: Bag of Tricks for Reward Modeling in LLMs
par: Liu, Chris Yuhao, et autres
Publié: (2024)

Semantic Mastery: Enhancing LLMs with Advanced Natural Language Understanding
par: Hariharan, Mohanakrishnan
Publié: (2025)

Evaluating LLMs Across Multi-Cognitive Levels: From Medical Knowledge Mastery to Scenario-Based Problem Solving
par: Zhou, Yuxuan, et autres
Publié: (2025)

Bag of Tricks: Benchmarking of Jailbreak Attacks on LLMs
par: Xu, Zhao, et autres
Publié: (2024)

Protoknowledge Shapes Behaviour of LLMs in Downstream Tasks: Memorization and Generalization with Knowledge Graphs
par: Ranaldi, Federico, et autres
Publié: (2025)

Alpaca against Vicuna: Using LLMs to Uncover Memorization of LLMs
par: Kassem, Aly M., et autres
Publié: (2024)

Memorization or Reasoning? Exploring the Idiom Understanding of LLMs
par: Kim, Jisu, et autres
Publié: (2025)

Mitigating Memorization in LLMs using Activation Steering
par: Suri, Manan, et autres
Publié: (2025)

Memorization Dynamics in Knowledge Distillation for Language Models
par: Borkar, Jaydeep, et autres
Publié: (2026)

Unveiling Over-Memorization in Finetuning LLMs for Reasoning Tasks
par: Ruan, Zhiwen, et autres
Publié: (2025)

Understanding Verbatim Memorization in LLMs Through Circuit Discovery
par: Lasy, Ilya, et autres
Publié: (2025)

The Mirage of Model Editing: Revisiting Evaluation in the Wild
par: Yang, Wanli, et autres
Publié: (2025)

Multi-Step Reasoning in Korean and the Emergent Mirage
par: Son, Guijin, et autres
Publié: (2025)

Seamless Language Expansion: Enhancing Multilingual Mastery in Self-Supervised Models
par: Xu, Jing, et autres
Publié: (2024)

Guess or Recall? Training CNNs to Classify and Localize Memorization in LLMs
par: Dentan, Jérémie, et autres
Publié: (2025)

SPARQL Query Generation with LLMs: Measuring the Impact of Training Data Memorization and Knowledge Injection
par: Gashkov, Aleksandr, et autres
Publié: (2025)

Is Chain-of-Thought Reasoning of LLMs a Mirage? A Data Distribution Lens
par: Zhao, Chengshuai, et autres
Publié: (2025)

Bidirectional LMs are Better Knowledge Memorizers? A Benchmark for Real-world Knowledge Injection
par: Zhang, Yuwei, et autres
Publié: (2025)

IndicGEC: Powerful Models, or a Measurement Mirage?
par: Vajjala, Sowmya
Publié: (2025)

Rote Learning Considered Useful: Generalizing over Memorized Data in LLMs
par: Wu, Qinyuan, et autres
Publié: (2025)

Beyond Math: Stories as a Testbed for Memorization-Constrained Reasoning in LLMs
par: Jiang, Yuxuan, et autres
Publié: (2024)

Beyond Memorization: A Rigorous Evaluation Framework for Medical Knowledge Editing
par: Chen, Shigeng, et autres
Publié: (2025)

Memorization Inheritance in Sequence-Level Knowledge Distillation for Neural Machine Translation
par: Dankers, Verna, et autres
Publié: (2025)

Memorizing is Not Enough: Deep Knowledge Injection Through Reasoning
par: Xu, Ruoxi, et autres
Publié: (2025)

The Landscape of Memorization in LLMs: Mechanisms, Measurement, and Mitigation
par: Xiong, Alexander, et autres
Publié: (2025)

Identifying Legal Holdings with LLMs: A Systematic Study of Performance, Scale, and Memorization
par: Arvin, Chuck
Publié: (2025)