Skip to content
Conference Open access

Memory efficiency and resource-rational encoding in sentence processing

2026 · Annual Meeting of the Association for Computational Linguistics · pp. 33603-33618 · 1 citation · 86 references
Computer Science

TL;DR

The results show how resource-rational models of WM allocation can be implemented in neural models simply and successfully, and point to a dissociation between WM retrieval mechanisms and the underlying memory representations in models of human sentence processing.

Abstract

There is a growing consensus that, in order to serve as models of human language processing, language models (LMs) need to be constrained in their use of memory for context, the analogue to human working memory (WM). Here we take a novel yet simple approach to constraining WM in language models, in a way that reflects models of human cognition where memory is treated as a limited resource and deployed strategically. In order to capture this constraint on memory encoding, we inject noise into the hidden representations of Transformer-based LMs at tunable rates. Then we train the models with a hybrid objective, such that they learn to maximize the performance of next-word prediction subject to explicit constraints on the total encoding precision. We find that explicit WM constraints improve the model’s alignment with human reading times. More importantly, we find that the need to manage encoding precision reshapes the nature of the models’ context representations, making them more compressed and categorical. Our results show how resource-rational models of WM allocation can be implemented in neural models simply and successfully, and point to a dissociation between WM retrieval mechanisms and the underlying memory representations in models of human sentence processing.

Read PDF

Similar papers

Preprint Aug 2026

Beyond Static and Linear: What Attention Constraints Best Fit Human Reading Times?

Transformer-based language models are widely used as models of human language processing, yet their attention mechanisms allow lossless access to the full preceding context, unlike the limited memory systems of humans. We hypothesize that installing memory constraints into transformers'attention mechanisms can improve their fit to human behavioral data. While previous work has explored individual constraints in isolation, we conduct a systematic comparison of multiple attention-based memory mechanisms across different model sizes and training corpora, evaluating both psychometric predictive power for human reading times and grammatical competence. We additionally compare static constraints, in which the constraint strength is fixed throughout training, to dynamic memory curricula. We find that constraints that are sensitive to the content of intervening tokens consistently achieve the highest alignment with human reading times, outperforming distance-based constraints. We observe a dissociation between psychometric fit and grammatical competence under dynamic memory curricula, suggesting that Transformers cannot serve as a one-size-fits-all cognitive model.

Lanni Bu, Xiulin Yang, Christian Clark et al. · 0 citations
Preprint Jul 2026

Memory Decoder at Scale: A Pretrained, Parametric Long-Term Memory

This work presents Memory Decoder at Scale, scaling memory models up to 6.9B parameters and pretraining them on 300B tokens, demonstrating that independently scaling pretrained memory offers a more parameter efficient path to improving language model performance.

Rubin Wei, Jiaqi Cao, Jiarui Wang et al. · 1 citation
Review Open access Aug 2026

Unifying the structures of language in a neural population code.

It is concluded that explaining how language can emerge from neural population codes, in both biological and artificial systems, will not be achieved through the incremental refinement of algebraic-symbolic theories but will demand new theoretical paradigms.

Samuel A. Nastase, Zaid Zada, A. Goldberg et al. · 0 citations
Aug 2026

Instructing the Learning of Language Model with the Token Interpretation to Improve Language Understanding

Pretrained language models (PLMs) have established state-of-the-art performance across diverse natural language understanding (NLU) tasks. This study reveals that seman-tic-rich explanations of lexical units can effectively guide PLM learning processes. We propose a novel language understanding enhancement method with token interpretation (LUETI) that addresses two critical limitations in conventional PLMs: Incomplete token semantics caused by isolated contextual learning and insufficient semantic encoding in embedding matrices. LUETI operates through dual mechanisms, augmenting token represen-tations by integrating hidden states with corresponding token interpretations and refining embedding spaces using interpretation-derived semantic vectors for token prediction. LUETI, which is implemented as a plug-in module for standard architectures, demonstrates significant improvements on BERT and GLM, achieving average performance gains of 3.36% and 4.87% respectively on the SuperGLUE benchmark with equivalent parameters and training data. Note that LUETI-equipped models attain comparable performance to baseline PLMs using only 60% of pretraining data. Findings establish token interpretation as a computationally efficient but semantically powerful enhancement strategy for language model pretraining.

Tianyi Chen, Yashen Wang, Huan Chang et al. · 0 citations
Review Jul 2026

Memory for Large Language Models

A systematic, architecture-centric taxonomy of memory in LLMs is presented, characterizes memory along three orthogonal axes: representation, update dynamics, and persistence, effectively bridging disparate architectural paradigms.

Sining Zhoubian, Dan Zhang, Evgeny Kharlamov et al. · 1 citation