Using the Tools of Cognitive Science to Understand Large Language Models at Different Levels of Analysis

Modern artificial intelligence systems, such as large language models, are increasingly powerful but also increasingly hard to understand. Recognizing this problem as analogous to the historical difficulties in understanding the human mind, we argue that methods developed in cognitive science can be useful for understanding large language models. We propose a framework for applying these methods based on Marr's three levels of analysis. By revisiting established cognitive science techniques relevant to each level and illustrating their potential to yield insights into the behavior and internal organization of large language models, we aim to provide a toolkit for making sense of these new kinds of minds.

Teasing Apart Architecture and Initial Weights as Sources of Inductive Bias in Neural Networks

Artificial neural networks can acquire many aspects of human knowledge from data, making them promising as models of human learning. But what those networks can learn depends upon their inductive biases -- the factors other than the data that influence the solutions they discover -- and the inductive biases of neural networks remain poorly understood, limiting our ability to draw conclusions about human learning from the performance of these systems. Cognitive scientists and machine learning researchers often focus on the architecture of a neural network as a source of inductive bias. In this paper we explore the impact of another source of inductive bias -- the initial weights of the network -- using meta-learning as a tool for finding initial weights that are adapted for specific problems. We evaluate four widely-used architectures -- MLPs, CNNs, LSTMs, and Transformers -- by meta-training 430 different models across three tasks requiring different biases and forms of generalization. We find that meta-learning can substantially reduce or entirely eliminate performance differences across architectures and data representations, suggesting that these factors may be less important as sources of inductive bias than is typically assumed. When differences are present, architectures and data representations that perform well without meta-learning tend to meta-train more effectively. Moreover, all architectures generalize poorly on problems that are far from their meta-training experience, underscoring the need for stronger inductive biases for robust generalization.

Minimization of Boolean Complexity in In-Context Concept Learning

What factors contribute to the relative success and corresponding difficulties of in-context learning for Large Language Models (LLMs)? Drawing on insights from the literature on human concept learning, we test LLMs on carefully designed concept learning tasks, and show that task performance highly correlates with the Boolean complexity of the concept. This suggests that in-context learning exhibits a learning bias for simplicity in a way similar to humans.

When a language model is optimized for reasoning, does it still show embers of autoregression? An analysis of OpenAI o1

In "Embers of Autoregression" (McCoy et al., 2023), we showed that several large language models (LLMs) have some important limitations that are attributable to their origins in next-word prediction. Here we investigate whether these issues persist with o1, a new system from OpenAI that differs from previous LLMs in that it is optimized for reasoning. We find that o1 substantially outperforms previous LLMs in many cases, with particularly large improvements on rare variants of common tasks (e.g., forming acronyms from the second letter of each word in a list, rather than the first letter). Despite these quantitative improvements, however, o1 still displays the same qualitative trends that we observed in previous systems. Specifically, o1 - like previous LLMs - is sensitive to the probability of examples and tasks, performing better and requiring fewer "thinking tokens" in high-probability settings than in low-probability ones. These results show that optimizing a language model for reasoning can mitigate but might not fully overcome the language model's probability sensitivity.

Deciphering the Factors Influencing the Efficacy of Chain-of-Thought: Probability, Memorization, and Noisy Reasoning

Chain-of-Thought (CoT) prompting has been shown to enhance the multi-step reasoning capabilities of Large Language Models (LLMs). However, debates persist about whether LLMs exhibit abstract generalization or rely on shallow heuristics when given CoT prompts. To understand the factors influencing CoT reasoning we provide a detailed case study of the symbolic reasoning task of decoding shift ciphers, where letters are shifted forward some number of steps in the alphabet. GPT-4 achieves zero accuracy on most shift ciphers with standard prompting, but with CoT its accuracy improves to an average of 32%. By focusing on a single relatively simple task, we are able to identify three factors that systematically affect CoT performance: the probability of the task's expected output (probability), what the model has implicitly learned during pre-training (memorization), and the number of intermediate operations involved in reasoning (noisy reasoning). We show that these factors can drastically influence the task accuracy; e.g., varying the output's probability of occurrence can shift accuracy from 26% to 70%. We also demonstrate that it is essential for the model to explicitly produce intermediate steps as output that can be conditioned on to increase the probability of the correct answer. Our experiments indicate that as long as the model does so, the validity of the demonstrations in the prompt does not matter. Overall, we conclude that CoT prompting performance reflects both memorization and a probabilistic version of genuine reasoning.

Is In-Context Learning a Type of Gradient-Based Learning? Evidence from the Inverse Frequency Effect in Structural Priming

Large language models (LLMs) have shown the emergent capability of in-context learning (ICL). One line of research has explained ICL as functionally performing gradient descent. In this paper, we introduce a new way of diagnosing whether ICL is functionally equivalent to gradient-based learning. Our approach is based on the inverse frequency effect (IFE) -- a phenomenon in which an error-driven learner is expected to show larger updates when trained on infrequent examples than frequent ones. The IFE has previously been studied in psycholinguistics because humans show this effect in the context of structural priming (the tendency for people to produce sentence structures they have encountered recently); the IFE has been used as evidence that human structural priming must involve error-driven learning mechanisms. In our experiments, we simulated structural priming within ICL and found that LLMs display the IFE, with the effect being stronger in larger models. We conclude that ICL is indeed a type of gradient-based learning, supporting the hypothesis that a gradient component is implicitly computed in the forward pass during ICL. Our results suggest that both humans and LLMs make use of gradient-based, error-driven processing mechanisms.

modeLing: A Novel Dataset for Testing Linguistic Reasoning in Language Models

We introduce modeLing, a novel benchmark of Linguistics Olympiad-style puzzles which tests few-shot reasoning in AI systems. Solving these puzzles necessitates inferring aspects of a language's grammatical structure from a small number of examples. Such puzzles provide a natural testbed for language models, as they require compositional generalization and few-shot inductive reasoning. Consisting solely of new puzzles written specifically for this work, modeLing has no risk of appearing in the training data of existing AI systems: this ameliorates the risk of data leakage, a potential confounder for many prior evaluations of reasoning. Evaluating several large open source language models and GPT on our benchmark, we observe non-negligible accuracy, demonstrating few-shot emergent reasoning ability which cannot merely be attributed to shallow memorization. However, imperfect model performance suggests that modeLing can be used to measure further progress in linguistic reasoning.

Distilling Symbolic Priors for Concept Learning into Neural Networks

Humans can learn new concepts from a small number of examples by drawing on their inductive biases. These inductive biases have previously been captured by using Bayesian models defined over symbolic hypothesis spaces. Is it possible to create a neural network that displays the same inductive biases? We show that inductive biases that enable rapid concept learning can be instantiated in artificial neural networks by distilling a prior distribution from a symbolic Bayesian model via meta-learning, an approach for extracting the common structure from a set of tasks. By generating the set of tasks used in meta-learning from the prior distribution of a Bayesian model, we are able to transfer that prior into a neural network. We use this approach to create a neural network with an inductive bias towards concepts expressed as short logical formulas. Analyzing results from previous behavioral experiments in which people learned logical concepts from a few examples, we find that our meta-trained models are highly aligned with human performance.

Deep de Finetti: Recovering Topic Distributions from Large Language Models

Large language models (LLMs) can produce long, coherent passages of text, suggesting that LLMs, although trained on next-word prediction, must represent the latent structure that characterizes a document. Prior work has found that internal representations of LLMs encode one aspect of latent structure, namely syntax; here we investigate a complementary aspect, namely the document's topic structure. We motivate the hypothesis that LLMs capture topic structure by connecting LLM optimization to implicit Bayesian inference. De Finetti's theorem shows that exchangeable probability distributions can be represented as a mixture with respect to a latent generating distribution. Although text is not exchangeable at the level of syntax, exchangeability is a reasonable starting assumption for topic structure. We thus hypothesize that predicting the next token in text will lead LLMs to recover latent topic distributions. We examine this hypothesis using Latent Dirichlet Allocation (LDA), an exchangeable probabilistic topic model, as a target, and we show that the representations formed by LLMs encode both the topics used to generate synthetic data and those used to explain natural corpus data.

Bayes in the age of intelligent machines

The success of methods based on artificial neural networks in creating intelligent machines seems like it might pose a challenge to explanations of human cognition in terms of Bayesian inference. We argue that this is not the case, and that in fact these systems offer new opportunities for Bayesian modeling. Specifically, we argue that Bayesian models of cognition and artificial neural networks lie at different levels of analysis and are complementary modeling approaches, together offering a way to understand human cognition that spans these levels. We also argue that the same perspective can be applied to intelligent machines, where a Bayesian approach may be uniquely valuable in understanding the behavior of large, opaque artificial neural networks that are trained on proprietary data.