Forgetting as a Feature: Cognitive Alignment of Large Language Models

• URL: http://arxiv.org/abs/2601.09726v1
• Date: Sun, 28 Dec 2025 10:43:00 GMT
• Title: Forgetting as a Feature: Cognitive Alignment of Large Language Models
• Authors: Hien Tran, Quinten Steenhuis, Alexandros Christoforos, Chadbourne Davis,
• Abstract summary: We show that Large Language Models (LLMs) exhibit systematic forgetting of past information.<n> Drawing inspiration from human memory dynamics, we model LLM inference as a probabilistic memory process governed by exponential decay.<n>Building on these observations, we propose probabilistic memory prompting, a lightweight strategy that shapes evidence integration to mimic human-like memory decay.
• Score: 39.146761527401424
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large Language Models (LLMs) are often evaluated against ideals of perfect Bayesian inference, yet growing evidence suggests that their in-context reasoning exhibits systematic forgetting of past information. Rather than viewing this behavior as a limitation, we reinterpret forgetting as a functional cognitive mechanism. Drawing inspiration from human memory dynamics, we model LLM inference as a probabilistic memory process governed by exponential decay. We introduce a benchmark suite that evaluates temporal reasoning, concept drift adaptation, and associative recall, enabling direct comparison between model behavior and human cognitive patterns. Our empirical results reveal that LLMs demonstrate forgetting rates analogous to human memory efficiency trade-offs between stability and adaptability. Building on these observations, we propose probabilistic memory prompting, a lightweight strategy that shapes evidence integration to mimic human-like memory decay, leading to improved long-horizon reasoning performance. Our findings position forgetting not as a failure mode, but as a principled mechanism for adaptive intelligence.

Related papers

• Reasoning aligns language models to human cognition [12.07126784684808]
  We introduce an active probabilistic reasoning task that cleanly separates sampling (actively acquiring evidence) from inference (integrating evidence toward a decision)<n> Benchmarking humans and a broad set of contemporary large language models against near-optimal reference policies reveals a consistent pattern.<n>This model places humans and models in a shared low-dimensional cognitive space, reproduces behavioral signatures across agents, and shows how chain-of-thought shifts language models toward human-like regimes of evidence accumulation and belief-to-choice mapping.
  arXiv  Detail & Related papers  (2026-02-09T14:13:39Z)
• Analyzing Reasoning Consistency in Large Multimodal Models under Cross-Modal Conflicts [74.47786985522762]
  We identify a critical failure mode termed textual inertia, where models tend to blindly adhere to the erroneous text while neglecting conflicting visual evidence.<n>We propose the LogicGraph Perturbation Protocol that structurally injects perturbations into the reasoning chains of diverse LMMs.<n>Results reveal that models successfully self-correct in less than 10% of cases and predominantly succumb to blind textual error propagation.
  arXiv  Detail & Related papers  (2026-01-07T16:39:34Z)
• More Than Irrational: Modeling Belief-Biased Agents [25.274115351731325]
  We introduce a class of computational-rational (CR) user models for cognitively-bounded agents acting optimally under biased beliefs.<n>We address the challenge of identifying the latent user-specific bound and inferring biased belief states from passive observations.<n>We show that our CR model generates intuitively plausible behaviors corresponding to different levels of memory capacity.
  arXiv  Detail & Related papers  (2025-11-15T21:14:37Z)
• Beyond Memorization: Extending Reasoning Depth with Recurrence, Memory and Test-Time Compute Scaling [60.63703438729223]
  We show how different architectures and training methods affect model multi-step reasoning capabilities.<n>We confirm that increasing model depth plays a crucial role for sequential computations.
  arXiv  Detail & Related papers  (2025-08-22T18:57:08Z)
• Sequence-to-Sequence Models with Attention Mechanistically Map to the Architecture of Human Memory Search [13.961239165301315]
  We show that foundational architectures in neural machine translation exhibit mechanisms that directly correspond to those specified in the Context Maintenance and Retrieval model of human memory.<n>We implement a neural machine translation model as a cognitive model of human memory search that is both interpretable and capable of capturing complex dynamics of learning.
  arXiv  Detail & Related papers  (2025-06-20T18:43:15Z)
• Dynamic Programming Techniques for Enhancing Cognitive Representation in Knowledge Tracing [125.75923987618977]
  We propose the Cognitive Representation Dynamic Programming based Knowledge Tracing (CRDP-KT) model.<n>It is a dynamic programming algorithm to optimize cognitive representations based on the difficulty of the questions and the performance intervals between them.<n>It provides more accurate and systematic input features for subsequent model training, thereby minimizing distortion in the simulation of cognitive states.
  arXiv  Detail & Related papers  (2025-06-03T14:44:48Z)
• The Reasoning-Memorization Interplay in Language Models Is Mediated by a Single Direction [34.86855316803838]
  We identify a set of linear features in the model's residual stream that govern the balance between genuine reasoning and memory recall.<n>We show that intervening in these reasoning features helps the model more accurately activate the most relevant problem-solving capabilities during answer generation.
  arXiv  Detail & Related papers  (2025-03-29T14:00:44Z)
• I Predict Therefore I Am: Is Next Token Prediction Enough to Learn Human-Interpretable Concepts from Data? [76.15163242945813]
  Large language models (LLMs) have led many to conclude that they exhibit a form of intelligence.<n>We introduce a novel generative model that generates tokens on the basis of human-interpretable concepts represented as latent discrete variables.
  arXiv  Detail & Related papers  (2025-03-12T01:21:17Z)
• Predictive Attractor Models [9.947717243638289]
  We propose textitPredictive Attractor Models (PAM), a novel sequence memory architecture with desirable generative properties. PAM avoids catastrophic forgetting by uniquely representing past context through lateral inhibition in cortical minicolumns. We show that PAM is trained with local computations through Hebbian plasticity rules in a biologically plausible framework.
  arXiv  Detail & Related papers  (2024-10-03T12:25:01Z)
• Evolvable Psychology Informed Neural Network for Memory Behavior Modeling [2.5258264040936305]
  This paper proposes a theory informed neural networks for memory behavior modeling named PsyINN. It constructs a framework that combines neural network with differentiating sparse regression, achieving joint optimization. On four large-scale real-world memory behavior datasets, the proposed method surpasses the state-of-the-art methods in prediction accuracy.
  arXiv  Detail & Related papers  (2024-08-23T01:35:32Z)
• Causal Estimation of Memorisation Profiles [58.20086589761273]
  Understanding memorisation in language models has practical and societal implications. Memorisation is the causal effect of training with an instance on the model's ability to predict that instance. This paper proposes a new, principled, and efficient method to estimate memorisation based on the difference-in-differences design from econometrics.
  arXiv  Detail & Related papers  (2024-06-06T17:59:09Z)
• Memory in humans and deep language models: Linking hypotheses for model augmentation [1.0485739694839669]
  We argue that memory-augmented Transformers can benefit substantially from considering insights from the memory literature in humans. We detail an approach to integrating evidence from the human memory system through the specification of cross-domain linking hypotheses.
  arXiv  Detail & Related papers  (2022-10-04T19:35:11Z)

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.