arXiv subjects

Kim Stachenfeld

Publications and source records attributed to Kim Stachenfeld.

4 recordsLinked to original sources

arXiv2026

Discovering Differences in Strategic Behavior Between Humans and LLMs

As Large Language Models (LLMs) are increasingly deployed in social and strategic scenarios, it becomes critical to understand where and why their behavior diverges from that of humans. While behavioral game theory (BGT) provides a framework for analyzing behavior, existing models do not fully capture the idiosyncratic behavior of humans or black-box, non-human agents like LLMs. We employ AlphaEvolve, a cutting-edge program discovery tool, to directly discover interpretable models of human and LLM behavior from data, thereby enabling open-ended discovery of structural factors driving human and LLM behavior. Our analysis on iterated rock-paper-scissors reveals that frontier LLMs can be capable of deeper strategic behavior than humans. These results provide a foundation for understanding structural differences driving differences in human and LLM behavior in strategic interactions.

cs.AI↗

arXiv2024

DeepSpeech models show Human-like Performance and Processing of Cochlear Implant Inputs

Cochlear implants(CIs) are arguably the most successful neural implant, having restored hearing to over one million people worldwide. While CI research has focused on modeling the cochlear activations in response to low-level acoustic features, we hypothesize that the success of these implants is due in large part to the role of the upstream network in extracting useful features from a degraded signal and learned statistics of language to resolve the signal. In this work, we use the deep neural network (DNN) DeepSpeech2, as a paradigm to investigate how natural input and cochlear implant-based inputs are processed over time. We generate naturalistic and cochlear implant-like inputs from spoken sentences and test the similarity of model performance to human performance on analogous phoneme recognition tests. Our model reproduces error patterns in reaction time and phoneme confusion patterns under noise conditions in normal hearing and CI participant studies. We then use interpretability techniques to determine where and when confusions arise when processing naturalistic and CI-like inputs. We find that dynamics over time in each layer are affected by context as well as input type. Dynamics of all phonemes diverge during confusion and comprehension within the same time window, which is temporally shifted backward in each layer of the network. There is a modulation of this signal during processing of CI which resembles changes in human EEG signals in the auditory stream. This reduction likely relates to the reduction of encoded phoneme identity. These findings suggest that we have a viable model in which to explore the loss of speech-related information in time and that we can use it to find population-level encoding signals to target when optimizing cochlear implant inputs to improve encoding of essential speech-related information and improve perception.

cs.NE↗

arXiv2024

When does compositional structure yield compositional generalization? A kernel theory

Compositional generalization (the ability to respond correctly to novel combinations of familiar components) is thought to be a cornerstone of intelligent behavior. Compositionally structured (e.g. disentangled) representations support this ability; however, the conditions under which they are sufficient for the emergence of compositional generalization remain unclear. To address this gap, we present a theory of compositional generalization in kernel models with fixed, compositionally structured representations. This provides a tractable framework for characterizing the impact of training data statistics on generalization. We find that these models are limited to functions that assign values to each combination of components seen during training, and then sum up these values ("conjunction-wise additivity"). This imposes fundamental restrictions on the set of tasks compositionally structured kernel models can learn, in particular preventing them from transitively generalizing equivalence relations. Even for compositional tasks that they can learn in principle, we identify novel failure modes in compositional generalization (memorization leak and shortcut bias) that arise from biases in the training data. Finally, we empirically validate our theory, showing that it captures the behavior of deep neural networks (convolutional networks, residual networks, and Vision Transformers) trained on a set of compositional tasks with similarly structured data. Ultimately, this work examines how statistical structure in the training data can affect compositional generalization, with implications for how to identify and remedy failure modes in deep learning models.

cs.LG↗

arXiv2023

Neuroscience needs Network Science

The brain is a complex system comprising a myriad of interacting elements, posing significant challenges in understanding its structure, function, and dynamics. Network science has emerged as a powerful tool for studying such intricate systems, offering a framework for integrating multiscale data and complexity. Here, we discuss the application of network science in the study of the brain, addressing topics such as network models and metrics, the connectome, and the role of dynamics in neural networks. We explore the challenges and opportunities in integrating multiple data streams for understanding the neural transitions from development to healthy function to disease, and discuss the potential for collaboration between network science and neuroscience communities. We underscore the importance of fostering interdisciplinary opportunities through funding initiatives, workshops, and conferences, as well as supporting students and postdoctoral fellows with interests in both disciplines. By uniting the network science and neuroscience communities, we can develop novel network-based methods tailored to neural circuits, paving the way towards a deeper understanding of the brain and its functions.

q-bio.NC↗