Memorization in Language Models

Follow this topic Ask about this topic

Momentum

10 papers in the last four weeks, up 150% on the four weeks before. 0.1% of all new papers.

Jul 13Week of Sep 28

Latest papers 75

All topics

A Verifiable Search Is Not a Learnable Chain-of-Thought
Jun 20, 2026Harsh PatelInference-Time Search Memorization in Language Models
Independent Researcher
Output Vector Editing for Memorization Mitigation in Large Language Models
Jun 17, 2026Ahmad Dawar Hakimi, Kaiwei Lei, Isabelle Augenstein +1Memorization in Language Models Neural Network Memorization
Center for Information and Language Processing, LMU Munich, Germany · Department of Computer Science, University of Copenhagen, Denmark · 3Munich Center for Machine Learning, Germany +1
On the Memorization Behavior of LLMs in Generative Recommendation: Observations, Implications, and Training Strategies
Jun 15, 2026Sunwoo Kim, Sunkyung Lee, Clark Mingxuan Ju +5Sequential Recommendation Memorization in Language Models
1KAIST · 2Sungkyunkwan University · 3Snap Inc.
AI Engram: In Search of Memory Traces in Artificial Intelligence
Jun 12, 2026Jea Kwon, Dong-Kyum Kim, Jiwon Kim +3Neural Representation Geometry Memorization in Language Models
Max Planck Institute for Security and Privacy (MPI-SP), Bochum, Germany · Seoul National University (SNU), Seoul, Korea · KAIST, Daejeon, Korea
The Holistic Storage of Verb+Up Phrases in Text-based and Audio-based Language Models
Jun 12, 2026Zachary Nicholas Houghton, Yu Zhou, Dan Pluth +2Memorization in Language Models Knowledge Representation
University of Oregon · Vail Systems, Inc
Detecting Functional Memorization in Code Language Models
Jun 11, 2026Matthieu Meeus, Anil Ramakrishna, Matthew Grange +2Memorization in Language Models LLM Auditing
Meta · Imperial College London
Reasoning or Memorization? Direction-Aware Diversity Exploration in LLM Reinforcement Learning
Jun 9, 2026Jiangnan Xia, Yucheng Shi, Yu Yang +3Memorization in Language Models RL for Language Model Reasoning
University of Georgia · Tencent AI Lab · The Education University of Hong Kong +1
Clinically Grounded Privacy Evaluation of Medical LMs
Jun 8, 2026Sasha Ronaghi, Sana Tonekaboni, Lena Stempfle +6Data Leakage Memorization in Language Models
1Stanford University · 2Massachusetts Institute of Technology · 3American Board of Family Medicine
MechLens: Late Crystallization of Factual Knowledge Explains Intervention Effectiveness in Language Models
Jun 6, 2026Xueping GaoMemorization in Language Models LLM Interpretability
Alibaba Cloud
LLMs Can Leak Training Data But Do They Want To? A Propensity-Aware Evaluation of Memorization in LLMs
Jun 4, 2026Gianluca Barmina, Peter Schneider-Kamp, Lukas Galke PoechData Leakage Memorization in Language Models
University of Southern Denmark
Not All Synthetic Data Is Yours to Learn From
May 29, 2026Sina Alemohammad, Li Chen, Richard G. Baraniuk +1Synthetic Data Pretraining Memorization in Language Models
ECE Department The University of Texas at Austin · Apple · ECE Department Rice University
How LoRA Remembers? A Parametric Memory Law for LLM Finetuning
May 28, 2026Ziwen Xu, Haiwen Hong, Linsong Yu +4Memorization in Language Models LLM Fine-Tuning
Zhejiang University · Alibaba Group
NumLeak: Public Numeric Benchmarks as Latent Labels in Foundation Models
May 28, 2026Anany KotawalaData Leakage LLM Evaluation
Princeton University, Princeton, NJ, USA.
Inferring the Size of Large Language Models From Popular Text Memorization
May 28, 2026Ivica NikolicParameter Estimation Memorization in Language Models
National University of Singapore
Why Can't They Remember? Uncovering Representation and Retrieval Bottlenecks in Multi-Turn Acoustic Memory
May 26, 2026Yang Xiao, Siyi Wang, Han Yin +4Audio-Language Model Evaluation Memorization in Language Models
1The University of Melbourne · 2KAIST · 3The University of Auckland +1
The Attribution Blind Spot: Detecting When Language Models Rely on Memory Rather Than Retrieved Context
May 26, 2026Zhe Yu, Wenpeng Xing, Yunzhao Wei +4Memorization in Language Models LLM Interpretability
Binjiang Institute of Zhejiang University · Zhejiang University · National Fintech Evaluation Center +2
Simulating Human Memory with Language Models
May 25, 2026Qihan Wang, Nicholas Tomlin, Michael Hu +2LLM Evaluation Memory-Augmented Language Models
NYU · UMass Amherst
Personalize-then-Store: Benchmarking and Learning Personalized Memory for Long-horizon Agents
May 25, 2026Yeonjun In, Wonjoong Kim, Sangwu Park +2Memorization in Language Models Persistent Memory for Language Models
KAIST
Extracting Training Data from Diffusion Language Models via Infilling
May 22, 2026Yihan Wang, N. AsokanData Leakage Masked Diffusion Models
University of Waterloo · KTH Royal Institute of Technology
Memorization Dynamics of Fill-in-the-Middle Pretraining
May 21, 2026Tobias von Arx, Tanguy DieudonnéLanguage Model Pretraining Memorization in Language Models
Department of Computer Science, ETH Zurich, Zurich, Switzerland.
Rethinking How to Remember: Beyond Atomic Facts in Lifelong LLM Agent Memory
May 19, 2026Jingwei Sun, Jianing Zhu, Jiangchao Yao +2Memorization in Language Models LLM Agent Memory
TMLR Group, Hong Kong Baptist University · The University of Texas at Austin · Shanghai Jiao Tong University +1
Auditing Reasoning-Trace Memorization Claims after Unlearning with Head-Conditioned Canaries
May 17, 2026Yanhang Li, Zhichao Fan, Zexin ZhuangMemorization in Language Models LLM Auditing
Northeastern University, USA · University of Illinois Urbana-Champaign, USA · Southern Methodist University, USA
Geometric Factual Recall in Transformers
May 12, 2026Shauli Ravfogel, Gilad Yehudai, Joan Bruna +1Neural Representation Geometry Memorization in Language Models
1New York University · 2Flatiron Institute
$δ$ -mem: Efficient Online Memory for Large Language Models
May 12, 2026Jingdi Lei, Di Zhang, Junxian Li +7Memory-Augmented Language Models Memorization in Language Models
Nanyang Technological University · Mind Lab · Fudan University +3
Memorize Theorems, Not Instances: Probing SFT Generalization through Mathematical Reasoning
May 10, 2026Ruiying Peng, Mengyu Yang, Jing Lei +3Supervised Fine-Tuning Memorization in Language Models
Tsinghua Shenzhen International Graduate School · Huawei Technologies
Human-Inspired Memory Architecture for LLM Agents
May 8, 2026Doga Kerestecioglu, Alexei Robsky, Clemens Vasters +2Memorization in Language Models LLM Agent Memory
Microsoft
When Graph Language Models Go Beyond Memorization
May 7, 2026Masatsugu Yamada, Mahito SugiyamaGraph Generation Memorization in Language Models
National Institute of Informatics Tokyo, Japan · National Institute of Informatics, Tokyo, Japan · SOKENDAI, Kanagawa, Japan
Attractor Geometry of Transformer Memory: From Conflict Arbitration to Confident Hallucination
May 7, 2026Qiyao Liang, Risto Miikkulainen, Ila FieteMemorization in Language Models Knowledge Conflicts in Language Models
Massachusetts Institute of Technology · University of Texas Austin, Cognizant · Cognizant
Memory as a Markov Matrix: Sample Efficient Knowledge Expansion via Token-to-Dictionary Mapping
May 5, 2026Kaustubh Pethkar, Ziyang Xiong, Zuofeng Shang +1Continual Learning for LLMs Memorization in Language Models
New Jersey Institute of Technology · University of California, Berkeley
Before Forgetting, Learn to Remember: Revisiting Foundational Learning Failures in LVLM Unlearning Benchmarks
May 5, 2026JuneHyoung Kwon, MiHyeon Kim, Eunju Lee +3VLM Evaluation VLM Unlearning
Department of Artificial Intelligence, Chung-Ang University · KT Corporation · Graduate School of Advanced Imaging Sciences, Multimedia and Film, Chung-Ang University

Jun 20, 2026, cs.LGJ/K move · Enter open · S save

A Verifiable Search Is Not a Learnable Chain-of-Thought

Harsh Patel

Independent Researcher

Inference-Time Search Memorization in Language Models CoT Distillation Neural Algorithmic Reasoning Algorithmic Reasoning

Open paper AskPDF arXiv

It is tempting to assume any task solvable by a short program can be taught to a model as its chain-of-thought: write the steps out, fine-tune, and the model follows. This paper shows the assumption fails for an identifiable class of procedures. The testbed is nine reasoning tasks, each from a deterministic generator; public and hidden splits share generators, so held-out data proxies test accuracy. I reverse-engineer the generators into Python solvers, render them as chain-of-thought, and distill into a rank-<= 32 LoRA over a 30B (3.5B-active) Nemotron model. Forward-computable tasks install readily: lookup/arithmetic and an 8-bit boolean task transfer (>= 0.99 and 0.68). Cryptarithm does not: distilling its backtracking search holds at 0.01-0.07 across eleven chain-of-thought designs, RL from verifiable rewards, and self-training, even though a search solver answers 71% of instances. This is not a capability gap. The model does the arithmetic on 97-100% of lines and ranks the correct cipher in its top eight on 71%; it cannot carry the search forward as a left-to-right derivation. Fine-tuning learns the shape of a verifiable elimination step while its verdicts become unconditional templates, correct only 16-57% of the time ("verdict-as-token"). The ceiling holds across backbones from 3B to 671B and across fine-tuning and prompting; a controlled intervention isolates the cause: revealing the cipher key, which turns the derivation forward, lifts the same instances from 0.03 to 0.57. When a procedure's only solution is search over information-free structure, no faithful forward chain-of-thought exists to imitate. The task becomes learnable only by removing the search, precomputing its combinatorial core into a catalog and reducing the trace to recall plus verification; the 1st-place solution reaches Private LB 0.92 this way. What distills is memorization and verification, not search.

Momentum

Related topics

Latest papers 75