Mechanisms
Memory Processes · Degradation
Motivated Forgetting
Example
Something happened that you would rather not revisit. A cue arrives, a place or a name, and you steer away rather than following it. Do that enough times and the memory becomes genuinely harder to reach, not merely unpleasant to reach. The record is intact. The route to it is not.
Motivated Forgetting in Humans
Definition
Motivated forgetting is the reduction in later recall of a memory that follows from deliberately stopping its retrieval when a reminder appears. It is measured with the think/no-think procedure, in which people first learn cue-target pairs, then see a subset of the cues and are told either to retrieve the associated target or to keep it out of awareness entirely, while a third set of learned pairs is never cued and serves as the baseline (Anderson & Green, 2001). Recall of the suppressed items falls below that baseline, the shortfall grows with the number of suppression attempts, and in the original experiments it held when memory was probed with a category cue that had never appeared in the study phase, which is the result that distinguishes inhibition of the memory itself from interference with one route to it (Anderson & Green, 2001). The mechanism is proposed to be inhibitory control over retrieval rather than decay or interference, recruiting the prefrontal machinery used to stop unwanted motor actions. Two subtypes are distinguished by the instruction given: direct suppression, in which the person blocks retrieval without putting anything in its place, and thought substitution, in which an alternative memory is retrieved to occupy awareness (Benoit & Anderson, 2012).
Neural Substrate
Retrieval suppression is associated with increased dorsolateral prefrontal activation and reduced hippocampal activation, with the magnitude of both predicting how much forgetting follows (Anderson et al., 2004). Two dissociable strategies contribute: direct suppression of retrieval, associated with right dorsolateral prefrontal cortex acting on the hippocampus, and thought substitution, associated with coupling between left caudal and left mid-ventrolateral prefrontal cortex, with hippocampal activation reduced only in the first case (Benoit & Anderson, 2012).
AI at a Glance
Humans decide for themselves that a memory should be harder to reach, and repeatedly declining to retrieve it makes it so, with the effect generalising in aggregate to cues never used during suppression (Anderson & Green, 2001; Clark et al., 2026). Nothing in a language model system generates that motive or accumulates that effect; the closest mechanisms are machine unlearning of weights (Yao et al., 2024), user-initiated deletion from a memory store, and instructed disregard within a conversation, all of which execute a decision made outside the system and none of which offers a guaranteed or cumulative removal (Le-Khac & Truong, 2025).
Motivated Forgetting in AI
How Far It Has Been Measured
Measurement in AI: Indirectly Measured
AI Memory Performance: Comparison Not Possible
Where It Lives in the System
What Has Been Measured
- No study located gives a language model the directed forgetting or think/no-think procedure, or tests people and AI on the same forget-on-instruction task; AI work instead appears under other names (in-context unlearning, machine unlearning, memory deletion), so the AI level is indirect (Wang & Sun, 2025).
- Current conversation: in a 2025 workshop paper, 30+ language models tracked repeatedly updated values in their context window (what the model can see in the conversation); explicitly telling models to forget earlier values improved accuracy by under 10 percentage points, and all models declined as outdated values piled up, with larger models declining more gradually (Wang & Sun, 2025).
- Current conversation: models fine-tuned to forget named facts when asked in the prompt (Llama 2 and Mistral) reached up to 95% forget accuracy while retaining 80% of unrelated knowledge, but the correct answer was still present in middle layers, so the models 'pretend to forget' rather than lose the information (Takashiro et al., 2025).
- Training: 'unlearning' methods meant to remove knowledge from a model's weights (its learned parameters) left it largely recoverable, with brief retraining on related facts restoring 88% of pre-unlearning accuracy (2024 preprint), a pattern reminiscent of suppressed but still-stored human memories (Deeb & Roger, 2024).
- Saved memory: a 2026 preprint on one model family (Gemma 3) found that deleting an exchange from the assistant's stored memory disclosed fewer deleted answers than simply instructing the model to forget, yet an attack could still tell the edited memory from one that never held the record (Ramesh, 2026).
- Agent memory benchmarks test forgetting outdated facts when they are replaced (selective forgetting in MemoryAgentBench, a 2025 preprint), finding that no tested system masters it, but they include no human baseline (Hu et al., 2025).
- Comparison is not possible because there is no common scale: human studies measure the drop in recall for items people were cued to forget or suppress, while AI studies measure intrusions from outdated information or leakage of deleted facts, and none reports human data on its task (Clark et al., 2026).
Where a Mechanism Can Live
04 Product
The whole configuration, and the only thing a benchmark observes directly.
01
Weights
Across deployments
02
Context Window
Within a session
03
Memory Layer
Across sessions
Which of the three a result belongs to is inferred from it, not seen in it.
Read more
Dorsolateral prefrontal cortex
Cortex in the prefrontal cortex
The upper outer surface of the prefrontal cortex, on and around the middle frontal gyrus, roughly Brodmann areas 9 and 46.
The dorsolateral prefrontal cortex sits on the lateral convexity of the frontal lobe, centered on the middle frontal gyrus and covering approximately Brodmann areas 9 and 46; its borders are drawn differently by different labs and no sulcus marks them. It is densely connected with posterior parietal cortex, the dorsal striatum, and the mediodorsal thalamus. Activity here tracks working-memory delays, task switching, and rule maintenance, and it is the usual target for prefrontal transcranial stimulation. Whether it stores the contents of working memory, holds the rules for acting on them, or simply reflects task difficulty is genuinely contested, and "executive function" names the dispute rather than settling it.
Hippocampus
Cortex in the hippocampal formation
A curved allocortical structure in the medial temporal lobe whose bilateral damage reliably produces dense anterograde amnesia in humans.
A paired, seahorse-shaped fold of three-layered cortex running front to back inside the temporal lobe, connected to the rest of the brain mainly through entorhinal cortex and the fornix. What it does is genuinely contested and has been for fifty years: the human lesion literature reads it as necessary for forming new declarative memories, the rodent recording literature as a map of space, and a third position treats both as instances of binding arbitrary elements into relations. The accounts differ on which species and which task they explain best, and the question of which is right remains open.
Prefrontal cortex
Cortex in the frontal lobe
The frontal cortex in front of the motor areas, defined classically by its connections with the mediodorsal thalamus rather than by any one function.
The prefrontal cortex occupies the front of the frontal lobe, anterior to premotor and motor cortex, and accounts for roughly a sixth to a quarter of human cortex depending on where the posterior border is drawn. Three competing definitions are in use (projection from the mediodorsal thalamus, the presence of a granular layer IV, and the absence of movement on electrical stimulation), and they do not enclose the same tissue, which is why rodent-to-primate homology is still argued over. It is reliably engaged by tasks with delays, rules, and conflicting options; what it contributes to those tasks is the open question, not whether it participates.
Ventrolateral prefrontal cortex
Cortex in the prefrontal cortex
The lower lateral prefrontal cortex, overlapping the inferior frontal gyrus and Brodmann areas 44, 45, and 47.
The ventrolateral prefrontal cortex runs along the inferior part of the lateral frontal surface, below the inferior frontal sulcus, and overlaps the inferior frontal gyrus almost entirely, so in the left hemisphere it shares tissue with what is called Broca's area. It connects strongly with temporal cortex, giving it a different input profile from its dorsolateral neighbor. It is engaged during retrieval of specific memories from semantic stores, response inhibition, and selection among competing alternatives. The right-hemisphere inhibition account and the left-hemisphere selection account developed in separate literatures, and whether one control operation covers both is not settled.
Anderson & Green (2001)
Suppressing unwanted memories by executive control
In
Nature, 410(6826), 366-369
Abstract
Freud proposed that unwanted memories can be forgotten by pushing them into the unconscious, a process called repression. The existence of repression has remained controversial for more than a century, in part because of its strong coupling with trauma, and the ethical and practical difficulties of studying such processes in controlled experiments. However, behavioural and neurobiological research on memory and attention shows that people have executive control processes directed at minimizing perceptual distraction, overcoming interference during short and long-term memory tasks and stopping strong habitual responses to stimuli. Here we show that these mechanisms can be recruited to...
Find it
Anderson et al. (2004)
Neural Systems Underlying the Suppression of Unwanted Memories
In
Science, 303(5655), 232-235
Abstract
Over a century ago, Freud proposed that unwanted memories can be excluded from awareness, a process called repression. It is unknown, however, how repression occurs in the brain. We used functional magnetic resonance imaging to identify the neural systems involved in keeping unwanted memories out of awareness. Controlling unwanted memories was associated with increased dorsolateral prefrontal activation, reduced hippocampal activation, and impaired retention of those memories. Both prefrontal cortical and right hippocampal activations predicted the magnitude of forgetting. These results confirm the existence of an active forgetting process and establish a neurobiological model for guiding...
Find it
Benoit & Anderson (2012)
Opposing Mechanisms Support the Voluntary Forgetting of Unwanted Memories
In
Neuron, 76(2), 450-460
Abstract
Reminders of the past can trigger the recollection of events that one would rather forget. Here, using fMRI, we demonstrate two distinct neural mechanisms that foster the intentional forgetting of such unwanted memories. Both mechanisms impair long-term retention by limiting momentary awareness of the memories, yet they operate in opposite ways. One mechanism, direct suppression, disengages episodic retrieval through the systemic inhibition of hippocampal processing that originates from right dorsolateral prefrontal cortex (PFC). The opposite mechanism, thought substitution, instead engages retrieval processes to occupy the limited focus of awareness with a substitute memory. It is...
Find it
Clark et al. (2026)
Forgetting as a consequence of retrieval suppression: A meta-analytic review.
In
Journal of Experimental Psychology: General, 155(5), 1318-1346
Abstract
Suppressing retrieval of a memory when faced with a reminder has been shown to reduce the probability of that memory coming to mind in the future, a phenomenon known as suppression-induced forgetting (SIF). However, efforts to observe SIF have sometimes failed, leading some to question the robustness of the effect. To address this issue, we conducted a comprehensive meta-analysis of SIF within the think/no-think paradigm including several key methodological variants to the original design. Across 500 effects from 120 studies, we observed a consistent aggregate SIF effect (d ≈ 0.20–0.40) measured using either same probe (SIF ≈ 6%), independent probe (SIF ≈ 5%–6%), or recognition (SIF ≈...
Find it
Deeb & Roger (2024)
Do Unlearning Methods Remove Information from Language Model Weights?
In
arXiv
Abstract
Large Language Models' knowledge of how to perform cyber-security attacks, create bioweapons, and manipulate humans poses risks of misuse. Previous work has proposed methods to unlearn this knowledge. Historically, it has been unclear whether unlearning techniques are removing information from the model weights or just making it harder to access. To disentangle these two objectives, we propose an adversarial evaluation method to test for the removal of information from model weights: we give an attacker access to some facts that were supposed to be removed, and using those, the attacker tries to recover other facts from the same distribution that cannot be guessed from the accessible...
Find it
Hu et al. (2025)
Evaluating Memory in LLM Agents via Incremental Multi-Turn Interactions
In
arXiv
Abstract
Recent benchmarks for Large Language Model (LLM) agents primarily focus on evaluating reasoning, planning, and execution capabilities, while another critical component-memory, encompassing how agents memorize, update, and retrieve long-term information-is under-evaluated due to the lack of benchmarks. We term agents with memory mechanisms as memory agents. In this paper, based on classic theories from memory science and cognitive science, we identify four core competencies essential for memory agents: accurate retrieval, test-time learning, long-range understanding, and selective forgetting. Existing benchmarks either rely on limited context lengths or are tailored for static,...
Find it
Le-Khac & Truong (2025)
A survey on large language models unlearning: taxonomy, evaluations, and future directions
In
Artificial Intelligence Review, 58(12)
Abstract
Following the introduction of data privacy regulations and “the right to be forgotten”, large language models (LLMs) unlearning has emerged as a promising data removal solution for compliance purposes, while also facilitating a diverse range of applications, including copyright protection, model detoxification and correction, and jailbreaking defence. In this survey, we present the taxonomy of existing LLMs unlearning algorithms, summarise unlearning evaluation methods including specialised benchmarks and threat models, and explore the applications of unlearning to provide a broad overview of the current state-of-the-art. We propose a novel problem formulation of LLMs unlearning with the...
Find it
Ramesh (2026)
Can an AI Assistant Really Forget? Auditable Deletion from Addressable Memory
In
arXiv
Abstract
An assistant can stop repeating a fact without removing it from memory. To study this difference, we install a support-vector gate in frozen Gemma 3 and record which stored keys and values belong to each exchange. A deletion request excludes the exchange's rows from the long-range readout and recalculates the gate on what remains. We check this operation against an independent refit, then compare it with running the model again on the conversation without the exchange. This second comparison matters because the exchange may already have influenced surviving memory rows. At 4B, the gated model passed checks for recall and feasible deletion on the same six of eight records admitted by the...
Find it
Takashiro et al. (2025)
Answer When Needed, Forget When Not: Language Models Pretend to Forget via In-Context Knowledge Unlearning
In
Findings of the Association for Computational Linguistics: ACL 2025, 24872-24885
Find it
Wang & Sun (2025)
Unable to Forget: Proactive Interference Reveals Working Memory Limits in LLMs Beyond Context Length
In
arXiv
Abstract
Information retrieval in Large Language Models (LLMs) is increasingly recognized as intertwined with generation capabilities rather than mere lookup. While longer contexts are often assumed to improve retrieval, the effects of intra-context interference remain understudied. To address this, we adapt the proactive interference (PI) paradigm from cognitive science, where earlier information disrupts recall of newer updates. In humans, susceptibility to such interference is inversely linked to working memory capacity. We introduce PI-LLM, an evaluation that sequentially streams semantically related key-value updates and queries only the final values. Although these final values are clearly...
Find it
Yao et al. (2024)
Machine Unlearning of Pre-trained Large Language Models
In
Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 8403-8419
Abstract
This study investigates the concept of the ‘right to be forgotten’ within the context of large language models (LLMs). We explore machine unlearning as a pivotal solution, with a focus on pre-trained models–a notably under-researched area. Our research delineates a comprehensive framework for machine unlearning in pre-trained LLMs, encompassing a critical analysis of seven diverse unlearning methods. Through rigorous evaluation using curated datasets from arXiv, books, and GitHub, we establish a robust benchmark for unlearning performance, demonstrating that these methods are over 105 times more computationally efficient than retraining. Our results show that integrating gradient ascent...
Find it