Parametric Memory

Follow this topic Ask about this topic

Momentum

2 papers in the last four weeks, down 33% on the four weeks before. 0.0% of all new papers.

Jul 6Week of Sep 21

Latest papers 23

All topics

MemoReason: Evaluating the Effect of Parametric Memory on Contextual Reasoning in LLMs
Sep 28, 2026Zineddine Tighidet, Andrea Mogini, Jiali Mei +2LLM Reasoning Strategies Contextual Reasoning
BNP Paribas Paris, France · Sorbonne Université Paris, France · Criteo AI Lab
Commutator Memory: Sparse, Path-Local Reading and Steering in Language Models
Sep 28, 2026John SweeneyModel Weights Parametric Memory
Sideplane AI
Complementary Roles of Activation and Parametric Memory in Few-Shot Learning
Sep 23, 2026Miaohe Niu, Runsong Zhao, Xinyu Liu +5Parametric Memory Few-Shot Learning
Northeastern University, Shenyang, China · NiuTrans Research, Shenyang, China
RPMem: Learning Long-Term Recurrent Parametric Memory Across Sessions for LLM Agents
Sep 20, 2026Fanyu Zhao, Ruike Cao, Liang Dong +6Parametric Memory Large Language Model Agents
Fudan University · Qwen Business Unit of Alibaba
Mitigating Identity Essentialism in LLM Agents with Longitudinal Life Trajectories
Aug 20, 2026Hexi Wang, Yujia Zhou, Bangde Du +7Scaling Improve Social Simulation Large Language Model Agents
Department of Computer Science and Technology, Tsinghua University · Quan Cheng Laboratory
The Sleeping Agent: What Gist-Based Context Compression Loses and Why
Aug 12, 2026Nicholas E. KyrkewoodConversational Memory Parametric Memory
Independent Researcher
Omni2LoRA: Coherence-Preserving Parametric Memory for Efficient Omni Language Models
Aug 10, 2026Puneet Mathur, Manan Suri, Dinesh ManochaOmni-Modal Multimodal Large Language Models
University of Maryland, College Park
Memory Decoder at Scale: A Pretrained, Parametric Long-Term Memory
Jul 30, 2026Rubin Wei, Jiaqi Cao, Jiarui Wang +4Parametric Memory Large Language Model Decoding
LUMIA Lab, School of Artificial Intelligence, Shanghai Jiao Tong University · Shanghai Artificial Intelligence Laboratory · Electronic Engineering, Tsinghua University
ForgetBench: Benchmarking Forgetting Dynamics of Long-Term Parametric Memory in Language Models
Jul 29, 2026Ruxi Gu, Zhenliang Zhang, Wei WangLarge Language Model Memory Catastrophic Forgetting
Department of Automation, University of Science and Technology of China, Hefei, China · State Key Laboratory of General Artificial Intelligence, BIGAI, Beijing, China · School of Computer and Communication Engineering, University of Science and Technology Beijing, Beijing, China.
UniMem: Complementary Episodic-to-Parametric Memory for Boundary-Agnostic Task Streams
Jul 28, 2026Siyu Xia, Chenheng Zhang, Yanting Wu +8Parametric Memory Episodic Memory
Institute of Automation, Chinese Academy of Sciences, Beijing, China · School of Artificial Intelligence, University of Chinese Academy of Sciences, China · State Key Lab of General Artificial Intelligence, School of Intelligence Science and Technology, Peking University +3
MemSFT: Mitigating Alignment Tax with an External Parametric Memory
Jul 28, 2026Jiarui Wang, Xiang Shi, Jiaqi Cao +8Parametric Memory Large Language Model Adaptation
LUMIA Lab, School of Artificial Intelligence, Shanghai Jiao Tong University · Shanghai AI Laboratory · School of Computer Science, Shanghai Jiao Tong University +1
Parametric Memory Decoding for Zero-Shot Routing in LoRA-Based External Parametric Memory
Jul 5, 2026Fengxian Ji, Zhuohan Xie, Jingpu Yang +3Parametric Memory Large Language Model Routing
1MBZUAI, United Arab Emirates · Institute of Automation, Chinese Academy of Sciences, China
Auditing Forgetting in Limited Memory Language Models
Jul 1, 2026Arya Raeesi, Hanna RoedLarge Language Model Unlearning Large Language Model Memory
University of California, Berkeley, Berkeley, California, United States of America.
Probing Memorization of Tabular In-Context Learning
Jun 30, 2026Francesco Capano, Jonas BöhlerParametric Memory Tabular Learning
SAP SE, Walldorf, Germany.
TrustMargin: Training-Free Arbitration between Parametric Memory and Retrieved Evidence in Large Language Models
Jun 7, 2026Jingyan Xu, Hong Shi, Yi Shan +4Large Language Model Reliability Question-Answering Benchmarks
DCST, Peking University · Beijing, China
Rethinking LoRA Memory Through the Lens of KV Cache Compression
Jun 4, 2026Chunsheng Zuo, Liaoyaqi Wang, William Jurayj +2Parametric Memory Key-Value Cache Compression
Johns Hopkins University
Scaling Self-Evolving Agents via Parametric Memory
Jun 3, 2026Tao Ren, Weiyao Luo, Hui Yang +8Parametric Memory Self-Evolving Agents
Qwen-Character Team · Alibaba Group · Peking University
How LoRA Remembers? A Parametric Memory Law for LLM Finetuning
May 28, 2026Ziwen Xu, Haiwen Hong, Linsong Yu +4Parametric Memory Large Language Model Fine-Tuning
Zhejiang University · Alibaba Group
ICICLE: Expanding Retrieval with In-Context Documents
May 26, 2026Yu-Chen Den, Yung-Yu Shih, Zhi Rui Tam +4In-Context Parametric Memory
1National Taiwan University, Taipei, Taiwan · 2Johns Hopkins University, Baltimore, US
Auto-Dreamer: Learning Offline Memory Consolidation for Language Agents
May 20, 2026Chongrui Ye, Yuxiang Liu, Yu Wang +5Conversational Memory Parametric Memory
University of Illinois Urbana-Champaign · University of California San Diego
PromptDx: Differentiable Prompt Tuning for Multimodal In-Context Alzheimer's Diagnosis
May 9, 2026Lujia Zhong, Yihao Xia, Shuo Huang +2Multimodal Clinical Data Alzheimer
Stevens Neuroimaging and Informatics Institute, Keck School of Medicine, University of Southern California · Ming Hsieh Department of Electrical and Computer Engineering, Viterbi School of Engineering, University of Southern California · Alfred E. Mann Department of Biomedical Engineering, Viterbi School of Engineering, University of Southern California
Evolving Token Communication with Parametric Memory Network
May 3, 2026Weixuan Chen, Qianqian YangSemantic Communications Parametric Memory
College of Information Science and Electronic Engineering, Zhejiang University, Hangzhou, China
A Parametric Memory Head for Continual Generative Retrieval
Apr 25, 2026Kidist Amde Mekonnen, Yubao Tang, Maarten de RijkeParametric Memory Documentation
University of Amsterdam Amsterdam, The Netherlands

Sep 28, 2026, cs.CLJ/K move · Enter open · S save

MemoReason: Evaluating the Effect of Parametric Memory on Contextual Reasoning in LLMs

Zineddine Tighidet, Andrea Mogini, Jiali Mei, Patrick Gallinari+1

BNP Paribas Paris, France · Sorbonne Université Paris, France · Criteo AI Lab

LLM Reasoning Strategies Contextual Reasoning Parametric Memory Reasoning Benchmark Factual Recall Memorization

Open paper AskPDF arXiv

Large Language Models (LLMs) perform well on reasoning benchmarks, but it remains unclear whether this reflects genuine contextual reasoning or reliance on facts memorized in their parameters. We investigate this by distinguishing two possibilities: a broad \textit{memorization bias}, where familiar content improves reasoning performance, and the \textit{Strong Parametric Shortcut Hypothesis}, where models skip reasoning entirely and recall stored answers. To test these effects, we introduce \textbf{MemoReason}, a human-curated benchmark that pairs factual reasoning tasks with structurally identical \fictitiousterm{} versions where real entities like people, companies, or dates are systematically replaced by \fictitiousterm{} ones of the same type. This \scorerevision{preserves task structure and specified reasoning operations} while varying the familiarity of the context, allowing controlled measurement of how the parametric memory affects reasoning. \revision{Our evaluation of recent LLMs reveals consistent and statistically significant performance drops of up to 15.7% in the fictitious setting, demonstrating a clear memorization bias.} However, a targeted analysis of \revision{questions failed in the fictitious setting} shows that models rarely respond with the corresponding factual answer, indicating that direct parametric shortcuts are not the dominant failure mode. These findings suggest that parametric memory influences reasoning through mechanisms more complex than simple factual recall. \textbf{MemoReason} provides a controlled framework for studying these mechanisms and for extending paired factual-fictitious{} evaluation to broader reasoning settings.

Momentum

Related topics

Latest papers 23