3 citations · 8 across the 17 of their papers we have counts for
19 papers
Post-training makes large language models less human-like
Marcel Binz, Elif Akata, Abdullah Almaatouq +76
Large language models (LLMs) are increasingly used as surrogates for human participants, but it remains unclear which models best capture human behavior and why. To address this, w…
Whither symbols in the era of advanced neural networks?
Thomas L. Griffiths, Brenden M. Lake, R. Thomas McCoy +2
Some of the strongest evidence that human minds should be thought about in terms of symbolic systems has been the way they combine ideas, produce novelty, and learn quickly. We arg…
Steering Risk Preferences in Large Language Models by Aligning Behavioral and Neural Representations
Jian-Qiao Zhu, Haijiang Yan, Thomas L. Griffiths
Changing the behavior of large language models (LLMs) can be as straightforward as editing the Transformer's residual streams using appropriately constructed "steering vectors." Th…
Recovering Event Probabilities from Large Language Model Embeddings via Axiomatic Constraints
Jian-Qiao Zhu, Haijiang Yan, Thomas L. Griffiths
Rational decision-making under uncertainty requires coherent degrees of belief in events. However, event probabilities generated by Large Language Models (LLMs) have been shown to…
Using Reinforcement Learning to Train Large Language Models to Explain Human Decisions
Jian-Qiao Zhu, Hanbo Xie, Dilip Arumugam +2
A central goal of cognitive modeling is to develop models that not only predict human behavior but also provide insight into the underlying cognitive mechanisms. While neural netwo…
Identifying and Mitigating the Influence of the Prior Distribution in Large Language Models
Liyi Zhang, Veniamin Veselovsky, R. Thomas McCoy +1
Large language models (LLMs) sometimes fail to respond appropriately to deterministic tasks -- such as counting or forming acronyms -- because the implicit prior distribution they…
Localized Cultural Knowledge is Conserved and Controllable in Large Language Models
Veniamin Veselovsky, Berke Argin, Benedikt Stroebl +5
Just as humans display language patterns influenced by their native tongue when speaking new languages, LLMs often default to English-centric responses even when generating in othe…
Convolutional Neural Networks Can (Meta-)Learn the Same-Different Relation
Max Gupta, Sunayana Rane, R. Thomas McCoy +1
While convolutional neural networks (CNNs) have come to match and exceed human performance in many settings, the tasks these models optimize for are largely constrained to the leve…
Levels of Analysis for Large Language Models
Alexander Y. Ku, Declan Campbell, Xuechunzi Bai +10
Modern artificial intelligence systems, such as large language models, are increasingly powerful but also increasingly hard to understand. Recognizing this problem as analogous to…
Teasing Apart Architecture and Initial Weights as Sources of Inductive Bias in Neural Networks
Gianluca Bencomo, Max Gupta, Ioana Marinescu +2
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…
Capturing the Complexity of Human Strategic Decision-Making with Machine Learning
Jian-Qiao Zhu, Joshua C. Peterson, Benjamin Enke +1
Understanding how people behave in strategic settings--where they make decisions based on their expectations about the behavior of others--is a long-standing problem in the behavio…
Deciphering the Factors Influencing the Efficacy of Chain-of-Thought: Probability, Memorization, and Noisy Reasoning
Akshara Prabhakar, Thomas L. Griffiths, R. Thomas McCoy
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 exhibi…
Eliciting the Priors of Large Language Models using Iterated In-Context Learning
Jian-Qiao Zhu, Thomas L. Griffiths
As Large Language Models (LLMs) are increasingly deployed in real-world settings, understanding the knowledge they implicitly use when making decisions is critical. One way to capt…
Language Models Trained to do Arithmetic Predict Human Risky and Intertemporal Choice
Jian-Qiao Zhu, Haijiang Yan, Thomas L. Griffiths
The observed similarities in the behavior of humans and Large Language Models (LLMs) have prompted researchers to consider the potential of using LLMs as models of human cognition.…
Distilling Symbolic Priors for Concept Learning into Neural Networks
Ioana Marinescu, R. Thomas McCoy, Thomas L. Griffiths
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 de…
Recovering Mental Representations from Large Language Models with Markov Chain Monte Carlo
Jian-Qiao Zhu, Haijiang Yan, Thomas L. Griffiths
Simulating sampling algorithms with people has proven a useful method for efficiently probing and understanding their mental representations. We propose that the same methods can b…
Incoherent Probability Judgments in Large Language Models
Jian-Qiao Zhu, Thomas L. Griffiths
Autoregressive Large Language Models (LLMs) trained for next-word prediction have demonstrated remarkable proficiency at producing coherent text. But are they equally adept at form…
Deep de Finetti: Recovering Topic Distributions from Large Language Models
Liyi Zhang, R. Thomas McCoy, Theodore R. Sumers +2
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 c…
Bayes in the age of intelligent machines
Thomas L. Griffiths, Jian-Qiao Zhu, Erin Grant +1
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 Baye…