This note presents a non-associative algebraic framework for the representation and computation of information items in high - dimensional space. This framework is consistent with the principles of spatial computing and with the empirical findings in cognitive science about memory. Computations are performed through a process of multiplication-like binding and non-associative interference-like bundling. Models that rely on associative bundling typically lose order information, which necessitates the use of auxiliary order structures, such as position markers, to represent sequential information that is important for cognitive tasks. In contrast, the non-associative bundling proposed allows the construction of sparse representations of arbitrarily long sequences that maintain their temporal structure across arbitrary lengths. The non-associative nature of the proposed framework results in the representation of a single sequence by two distinct states. The L-state, generated through left-associative bundling, continuously updates and emphasises a recency effect, while the R-state, formed through right-associative bundling, encodes finite sequences or chunks, capturing a primacy effect. The construction of these states may be associated with activity in the prefrontal cortex in relation to short-term memory and hippocampal encoding in long-term memory, respectively. The accuracy of retrieval is contingent upon a decision-making process that is based on the mutual information between the memory states and the cue. The model is able to replicate the Serial Position Curve, which reflects the empirical recency and primacy effects observed in cognitive experiments. Keywords: Memory states, high-dimensional computing (VSA), nonassociative bundling, spatial computing, mutual information, Serial Position Curve T o appear in Neural Computation, V ol 37, Issue 6, June 2025 1 Introduction In essence, the perception of an object is initialised with the activation of a sensory pole. This sensory activation has a rapid decay and lasts for only a few milliseconds.

We investigate the choice patterns of Large Language Models (LLMs) in the context of Decisions from Experience tasks that involve repeated choice and learning from feedback, and compare their behavior to human participants. We find that on the aggregate, LLMs appear to display behavioral biases similar to humans: both exhibit underweighting rare events and correlation effects. However, more nuanced analyses of the choice patterns reveal that this happens for very different reasons. LLMs exhibit strong recency biases, unlike humans, who appear to respond in more sophisticated ways. While these different processes may lead to similar behavior on average, choice patterns contingent on recent events differ vastly between the two groups. Specifically, phenomena such as ``surprise triggers change" and the ``wavy recency effect of rare events" are robustly observed in humans, but entirely absent in LLMs. Our findings provide insights into the limitations of using LLMs to simulate and predict humans in learning environments and highlight the need for refined analyses of their behavior when investigating whether they replicate human decision making tendencies.

We investigate in-context temporal biases in attention heads and transformer outputs. Using cognitive science methodologies, we analyze attention scores and outputs of the GPT-2 models of varying sizes. Across attention heads, we observe effects characteristic of human episodic memory, including temporal contiguity, primacy and recency. Transformer outputs demonstrate a tendency toward in-context serial recall. Importantly, this effect is eliminated after the ablation of the induction heads, which are the driving force behind the contiguity effect. Our findings offer insights into how transformers organize information temporally during in-context learning, shedding light on their similarities and differences with human memory and learning.

Large Language Models (LLMs) have shown remarkable capabilities in zero-shot learning applications, generating responses to queries using only pre-training information without the need for additional fine-tuning. This represents a significant departure from traditional machine learning approaches. Previous research has indicated that LLMs may exhibit serial position effects, such as primacy and recency biases, which are well-documented cognitive biases in human psychology. Our extensive testing across various tasks and models confirms the widespread occurrence of these effects, although their intensity varies. We also discovered that while carefully designed prompts can somewhat mitigate these biases, their effectiveness is inconsistent. These findings underscore the significance of serial position effects during the inference process, particularly in scenarios where there are no ground truth labels, highlighting the need for greater focus on addressing these effects in LLM applications.

In recent years, large language models (LLMs) have become incredibly popular, with ChatGPT for example being used by over a billion users. While these models exhibit remarkable language understanding and logical prowess, a notable challenge surfaces in the form of "hallucinations." This phenomenon results in LLMs outputting misinformation in a confident manner, which can lead to devastating consequences with such a large user base. However, we question the appropriateness of the term "hallucination" in LLMs, proposing a psychological taxonomy based on cognitive biases and other psychological phenomena. Our approach offers a more fine-grained understanding of this phenomenon, allowing for targeted solutions. By leveraging insights from how humans internally resolve similar challenges, we aim to develop strategies to mitigate LLM hallucinations. This interdisciplinary approach seeks to move beyond conventional terminology, providing a nuanced understanding and actionable pathways for improvement in LLM reliability.

Large Language Models (LLMs) are huge artificial neural networks which primarily serve to generate text, but also provide a very sophisticated probabilistic model of language use. Since generating a semantically consistent text requires a form of effective memory, we investigate the memory properties of LLMs and find surprising similarities with key characteristics of human memory. We argue that the human-like memory properties of the Large Language Model do not follow automatically from the LLM architecture but Figure 1: Recall accuracy for a serial memory are rather learned from the statistics of the experiment with human subjects (sample training textual data. These results strongly data from [4]) and for a memorization experiment suggest that the biological features of human of a list of 20 facts of the has-a type for memory leave an imprint on the way that we the Large Language Model GPT-J [5] studied structure our textual narratives.

Dr. Eng Lim Goh, vice president and chief technology officer for high-performance computing and artificial intelligence at Hewlett Packard Enterprise, has spent his career considering what machines can do, what they might do, and what they shouldn't do. As AI has become more prominent, he has been asked to play the role of futurist by the customers and partners he deals with daily. Goh, like most scientists, is unwilling to roll out any sort of crystal ball. But given his long familiarity with computer graphics, machine learning, analytics, and data, he is in a good position to talk about the different viewpoints on the subject. In this Q&A, he outlines the promises and concerns introduced by the ongoing uptick in AI adoption.