ForgetBench: Benchmarking Forgetting Dynamics of Long-Term Parametric Memory in Language Models

• URL: http://arxiv.org/abs/2607.26455v1
• Date: Wed, 29 Jul 2026 04:11:30 GMT
• Title: ForgetBench: Benchmarking Forgetting Dynamics of Long-Term Parametric Memory in Language Models
• Abstract summary: ForgetBench is a benchmark designed to systematically characterize forgetting behavior in large language models.<n>Building upon a sequential relational editing framework, we construct temporally ordered knowledge streams and evaluate model behavior across multiple editing stages.
• Score: 3.8463085098862178
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large language models (LLMs) have demonstrated strong capabilities in knowledge acquisition and reasoning, yet their ability to retain previously acquired knowledge under repeated updates remains insufficiently understood. Existing evaluation paradigms primarily focus on single-step reasoning or static knowledge editing, which fail to capture the temporal dynamics of knowledge retention and degradation during continual model modification. In this work, we propose ForgetBench, a benchmark designed to systematically characterize forgetting behavior in LLMs under continual knowledge editing. ForgetBench introduces two complementary evaluation paradigms, namely concept-based QA and scenario-based QA, to disentangle isolated factual retention from structured relational knowledge preservation. Building upon a sequential editing framework, we construct temporally ordered knowledge streams and evaluate model behavior across multiple editing stages. To quantitatively analyze long-term retention dynamics, we further introduce a unified evaluation framework that models knowledge evolution over time, enabling the measurement of temporal decay, retention strength, and cross-instance stability. Extensive experiments across diverse models and editing methods demonstrate that existing approaches fail to strike a balance between long-term retention and generalization quality. Our findings highlight the need for more robust memory mechanisms that can effectively acquire, update, and preserve knowledge over time in future LLMs. Code will be released upon acceptance.

Related papers

• Dynamic Mixture of Latent Memories for Self-Evolving Agents [57.20419419302731]
  MoLEM is a generative mixture of latent memory framework based on a dynamic mixture-of-experts (MoE)<n>We train the framework on continual-learning sequences spanning math, science, and code domains.<n>After the full continual-learning sequence, our method improves the average accuracy by 10.40% over the Vanilla pretrained baseline.
  arXiv  Detail & Related papers  (2026-05-21T03:35:10Z)
• The Model Agreed, But Didn't Learn: Diagnosing Surface Compliance in Large Language Models [12.743453676247903]
  Large Language Models (LLMs) internalize vast world knowledge as parametric memory, yet inevitably inherit the staleness and errors of their source corpora.<n> Knowledge editing offers a pivotal paradigm for surgically modifying memory without retraining.<n>We introduce a diagnostic framework that subjects models to discriminative self-assessment under in-context learning settings.
  arXiv  Detail & Related papers  (2026-04-07T15:20:41Z)
• Can Large Language Models Keep Up? Benchmarking Online Adaptation to Continual Knowledge Streams [78.9560820155271]
  We evaluate online adaptation over streaming, continually updating knowledge.<n> OAKS comprises two datasets: OAKS-BABI and OAKS-Novel.<n>Both state-of-the-art models and agentic memory systems fail to adapt robustly on OAKS.
  arXiv  Detail & Related papers  (2026-03-08T00:38:39Z)
• Modular Memory is the Key to Continual Learning Agents [100.09688599754465]
  We argue that combining the strengths of In-Weight Learning (IWL) and the newly emerged capabilities of In-Context Learning (ICL) through the design of modular memory is the missing piece for continual adaptation at scale.<n>We outline a conceptual framework for modular memory-centric architectures that leverage ICL for rapid adaptation and knowledge accumulation, and IWL for stable updates to model capabilities.
  arXiv  Detail & Related papers  (2026-03-02T11:40:05Z)
• KnowMT-Bench: Benchmarking Knowledge-Intensive Long-Form Question Answering in Multi-Turn Dialogues [58.305425399644086]
  Multi-Turn Long-Form Question Answering (MT-LFQA) is a key application paradigm of Large Language Models (LLMs) in knowledge-intensive domains.<n>We introduce textbfKnowMT-Bench, the textitfirst-ever benchmark designed to systematically evaluate MT-LFQA for LLMs across knowledge-intensive fields.
  arXiv  Detail & Related papers  (2025-09-26T04:32:29Z)
• TRAIL: Joint Inference and Refinement of Knowledge Graphs with Large Language Models [5.678291291711662]
  TRAIL is a novel, unified framework for Thinking, Reasoning, And Incremental Learning.<n>It couples joint inference and dynamic KG refinement with large language models.<n>Extensive experiments on multiple benchmarks demonstrate that TRAIL outperforms existing KG-augmented and retrieval-augmented LLM baselines by 3% to 13%.
  arXiv  Detail & Related papers  (2025-08-06T14:25:05Z)
• Enhancing LLM Reliability via Explicit Knowledge Boundary Modeling [41.19330514054401]
  Large language models (LLMs) are prone to hallucination stemming from misaligned self-awareness.<n>We propose the Explicit Knowledge Boundary Modeling framework to integrate fast and slow reasoning systems to harmonize reliability and usability.
  arXiv  Detail & Related papers  (2025-03-04T03:16:02Z)
• Stable Hadamard Memory: Revitalizing Memory-Augmented Agents for Reinforcement Learning [64.93848182403116]
  Current deep-learning memory models struggle in reinforcement learning environments that are partially observable and long-term. We introduce the Stable Hadamard Memory, a novel memory model for reinforcement learning agents. Our approach significantly outperforms state-of-the-art memory-based methods on challenging partially observable benchmarks.
  arXiv  Detail & Related papers  (2024-10-14T03:50:17Z)
• Temporal-Difference Variational Continual Learning [77.92320830700797]
  We propose new learning objectives that integrate the regularization effects of multiple previous posterior estimations.<n>Our approach effectively mitigates Catastrophic Forgetting, outperforming strong Variational CL methods.
  arXiv  Detail & Related papers  (2024-10-10T10:58:41Z)
• Uncertainty-preserving deep knowledge tracing with state-space models [1.3791394805787949]
  A central goal of knowledge tracing and traditional assessment is to quantify student knowledge and skills at a given point in time. We introduce Dynamic LENS, a modeling paradigm that combines the flexible uncertainty-preserving properties of variational autoencoders with the principled information integration of Bayesian state-space models.
  arXiv  Detail & Related papers  (2024-07-09T13:40:28Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.