Christopher J. Honey

Shima Rahimi Moghaddam, Christopher J. Honey

Large language models (LLMs) excel in many tasks in 2023, but they still face challenges in complex reasoning. Theory-of-mind (ToM) tasks, which require understanding agents' beliefs, goals, and mental states, are essential for common-sense reasoning involving humans, making it crucial to enhance LLM performance in this area. This study measures the ToM performance of GPT-4 and three GPT-3.5 variants (Davinci-2, Davinci-3, GPT-3.5-Turbo), and investigates the effectiveness of in-context learning in improving their ToM comprehension. We evaluated prompts featuring two-shot chain of thought reasoning and step-by-step thinking instructions. We found that LLMs trained with Reinforcement Learning from Human Feedback (RLHF) (all models excluding Davinci-2) improved their ToM accuracy via in-context learning. GPT-4 performed best in zero-shot settings, reaching nearly 80% ToM accuracy, but still fell short of the 87% human accuracy on the test set. However, when supplied with prompts for in-context learning, all RLHF-trained LLMs exceeded 80% ToM accuracy, with GPT-4 reaching 100%. These results demonstrate that appropriate prompting enhances LLM ToM reasoning, and they underscore the context-dependent nature of LLM cognitive capacities.

Hsiang-Yun Sherry Chien, Javier S. Turek, Nicole Beckage et al.

Sequential information contains short- to long-range dependencies; however, learning long-timescale information has been a challenge for recurrent neural networks. Despite improvements in long short-term memory networks (LSTMs), the forgetting mechanism results in the exponential decay of information, limiting their capacity to capture long-timescale information. Here, we propose a power law forget gate, which instead learns to forget information along a slower power law decay function. Specifically, the new gate learns to control the power law decay factor, p, allowing the network to adjust the information decay rate according to task demands. Our experiments show that an LSTM with power law forget gates (pLSTM) can effectively capture long-range dependencies beyond hundreds of elements on image classification, language modeling, and categorization tasks, improving performance over the vanilla LSTM. We also inspected the revised forget gate by varying the initialization of p, setting p to a fixed value, and ablating cells in the pLSTM network. The results show that the information decay can be controlled by the learnable decay factor p, which allows pLSTM to achieve its superior performance. Altogether, we found that LSTM with the proposed forget gate can learn long-term dependencies, outperforming other recurrent networks in multiple domains; such gating mechanism can be integrated into other architectures for improving the learning of long timescale information in recurrent neural networks.

Shima Rahimi Moghaddam, Fanjun Bu, Christopher J. Honey

In the human brain, internal states are often correlated over time (due to local recurrence and other intrinsic circuit properties), punctuated by abrupt transitions. At first glance, temporal smoothness of internal states presents a problem for learning input-output mappings (e.g. category labels for images), because the internal representation of the input will contain a mixture of current input and prior inputs. However, when training with naturalistic data (e.g. movies) there is also temporal autocorrelation in the input. How does the temporal "smoothness" of internal states affect the efficiency of learning when the training data are also temporally smooth? How does it affect the kinds of representations that are learned? We found that, when trained with temporally smooth data, "slow" neural networks (equipped with linear recurrence and gating mechanisms) learned to categorize more efficiently than feedforward networks. Furthermore, networks with linear recurrence and multi-timescale gating could learn internal representations that "un-mixed" quickly-varying and slowly-varying data sources. Together, these findings demonstrate how a fundamental property of cortical dynamics (their temporal autocorrelation) can serve as an inductive bias, leading to more efficient category learning and to the representational separation of fast and slow sources in the environment.