We use cookies to analyze the browsing and usage of our website and to personalize your experience. You can disable these technologies at any time, but this may limit certain functionalities of the site. Read our Privacy Policy for more information.
Setting cookies
You can enable and disable the types of cookies you wish to accept. However certain choices you make could affect the services offered on our sites (e.g. suggestions, personalised ads, etc.).
Essential cookies
These cookies are necessary for the operation of the site and cannot be deactivated. (Still active)
Analytics cookies
Do you accept the use of cookies to measure the audience of our sites?
Multimedia Player
Do you accept the use of cookies to display and allow you to watch the video content hosted by our partners (YouTube, etc.)?
Publications
The Roles of Neural Networks in Language Acquisition
How can modern neural networks like language models be useful to the field of language acquisition, and more broadly cognitive science, if t… (see more)hey are not a priori designed to be cognitive models? As developments towards natural language understanding and generation have improved leaps and bounds, with models like GPT‐4, the question of how they can inform our understanding of human language acquisition has re‐emerged. As such, it is critical to examine how in practice linking hypotheses between models and human learners can be safely established. To address these questions, we propose a model taxonomy, including four modelling approaches, each having differing goals, from exploratory hypothesis generation to hypothesis differentiation and testing. We show how the goals of these approaches align with the overarching goals of science and linguistics by connecting our taxonomy to the realist versus instrumentalist approaches in philosophy of science. We survey recent work having adopted each of our modelling approaches and address the importance of computational modelling in language acquisition studies.
How can modern neural networks like language models be useful to the field of language acquisition, and more broadly cognitive science, if t… (see more)hey are not a priori designed to be cognitive models? As developments towards natural language understanding and generation have improved leaps and bounds, with models like GPT‐4, the question of how they can inform our understanding of human language acquisition has re‐emerged. As such, it is critical to examine how in practice linking hypotheses between models and human learners can be safely established. To address these questions, we propose a model taxonomy, including four modelling approaches, each having differing goals, from exploratory hypothesis generation to hypothesis differentiation and testing. We show how the goals of these approaches align with the overarching goals of science and linguistics by connecting our taxonomy to the realist versus instrumentalist approaches in philosophy of science. We survey recent work having adopted each of our modelling approaches and address the importance of computational modelling in language acquisition studies.
The dominant paradigm for RLHF is online and on-policy RL: synchronously generating from the large language model (LLM) policy, labelling wi… (see more)th a reward model, and learning using feedback on the LLM's own outputs. While performant, this paradigm is computationally inefficient. Inspired by classical deep RL literature, we propose separating generation and learning in RLHF. This enables asynchronous generation of new samples while simultaneously training on old samples, leading to faster training and more compute-optimal scaling. However, asynchronous training relies on an underexplored regime, online but off-policy RLHF: learning on samples from previous iterations of our model. To understand the challenges in this regime, we investigate a fundamental question: how much off-policyness can we tolerate for asynchronous training to speed up learning but maintain performance? Among several RLHF algorithms we tested, we find that online DPO is most robust to off-policy data, and robustness increases with the scale of the policy model. We study further compute optimizations for asynchronous RLHF but find that they come at a performance cost, giving rise to a trade-off. Finally, we verify the scalability of asynchronous RLHF by training LLaMA 3.1 8B on an instruction-following task 40% faster than a synchronous run while matching final performance.
Learning reinforcement learning policies to control individual robots is often computationally non-economical because minor variations in ro… (see more)bot morphology (e.g. dynamics or number of limbs) can negatively impact policy performance. This limitation has motivated morphology agnostic policy learning, in which a monolithic deep learning policy learns to generalize between robotic morphologies. Unfortunately, these policies still have sub-optimal zero-shot performance compared to end-to-end finetuning on target morphologies. This limitation has ramifications in practical robotic applications, as online finetuning large neural networks can require immense computation. In this work, we investigate \textit{parameter efficient finetuning} techniques to specialize morphology-agnostic policies to a target robot that minimizes the number of learnable parameters adapted during online learning. We compare direct finetuning, which update subsets of the base model parameters, and input-learnable approaches, which add additional parameters to manipulate inputs passed to the base model. Our analysis concludes that tuning relatively few parameters (0.01\% of the base model) can measurably improve policy performance over zero shot. These results serve a prescriptive purpose for future research for which scenarios certain PEFT approaches are best suited for adapting policy's to new robotic morphologies.
The primary motor cortex is involved in initiation and adaptive control of locomotion. However, the role of the motor cortex in controlling … (see more)gait trajectories remains unclear. In animals, cortical neuromodulation allows for precise control of step height. We hypothesized that a similar control framework applies to humans, whereby cortical stimulation would primarily increase foot elevation. Transcranial magnetic stimulation (TMS) was applied over the motor cortex to assess the involvement of the corticospinal tract over the limb trajectory during human walking. Eight healthy adults (aged 20-32 years) participated in treadmill walking at 1.5 km/h. TMS was applied over the left motor cortex at an intensity of 120% of the threshold to elicit a dorsiflexion of the right ankle during the swing phase of gait. Electromyographic (EMG) measurements and three-dimensional (3D) lower limb kinematics were collected. When delivered during the early swing phase, TMS led to a significant increase in the maximum height of the right toe by a mean of 40.7% ± 14.9% (25.6mm ± 9.4 mm, p = 0.0352) and knee height by 57.8%± 16.8%; (32mm ± 9.3 mm; p = 0.008) across participants. These findings indicate that TMS can influence limb trajectory during walking, highlighting its potential as a tool for studying cortical control of locomotion.
Large language models (LLMs) are increasingly used as alternatives to traditional search engines given their capacity to generate text that … (see more)resembles human language. However, this shift is concerning, as LLMs often generate hallucinations, misleading or false information that appears highly credible. In this study, we explore the phenomenon of hallucinations across multiple languages in freeform text generation, focusing on what we call multilingual hallucination gaps. These gaps reflect differences in the frequency of hallucinated answers depending on the prompt and language used. To quantify such hallucinations, we used the FactScore metric and extended its framework to a multilingual setting. We conducted experiments using LLMs from the LLaMA, Qwen, and Aya families, generating biographies in 19 languages and comparing the results to Wikipedia pages. Our results reveal variations in hallucination rates, especially between high and low resource languages, raising important questions about LLM multilingual performance and the challenges in evaluating hallucinations in multilingual freeform text generation.
Large language models (LLMs) are increasingly used as alternatives to traditional search engines given their capacity to generate text that … (see more)resembles human language. However, this shift is concerning, as LLMs often generate hallucinations, misleading or false information that appears highly credible. In this study, we explore the phenomenon of hallucinations across multiple languages in freeform text generation, focusing on what we call multilingual hallucination gaps. These gaps reflect differences in the frequency of hallucinated answers depending on the prompt and language used. To quantify such hallucinations, we used the FactScore metric and extended its framework to a multilingual setting. We conducted experiments using LLMs from the LLaMA, Qwen, and Aya families, generating biographies in 19 languages and comparing the results to Wikipedia pages. Our results reveal variations in hallucination rates, especially between high and low resource languages, raising important questions about LLM multilingual performance and the challenges in evaluating hallucinations in multilingual freeform text generation.
Large language models (LLMs) are increasingly used as alternatives to traditional search engines given their capacity to generate text that … (see more)resembles human language. However, this shift is concerning, as LLMs often generate hallucinations, misleading or false information that appears highly credible. In this study, we explore the phenomenon of hallucinations across multiple languages in freeform text generation, focusing on what we call multilingual hallucination gaps. These gaps reflect differences in the frequency of hallucinated answers depending on the prompt and language used. To quantify such hallucinations, we used the FactScore metric and extended its framework to a multilingual setting. We conducted experiments using LLMs from the LLaMA, Qwen, and Aya families, generating biographies in 19 languages and comparing the results to Wikipedia pages. Our results reveal variations in hallucination rates, especially between high and low resource languages, raising important questions about LLM multilingual performance and the challenges in evaluating hallucinations in multilingual freeform text generation.
Current multi-task reinforcement learning (MTRL) methods have the ability to perform a large number of tasks with a single policy. However w… (see more)hen attempting to interact with a new domain, the MTRL agent would need to be re-trained due to differences in domain dynamics and structure. Because of these limitations, we are forced to train multiple policies even though tasks may have shared dynamics, leading to needing more samples and is thus sample inefficient. In this work, we explore the ability of MTRL agents to learn in various domains with various dynamics by simultaneously learning in multiple domains, without the need to fine-tune extra policies. In doing so we find that a MTRL agent trained in multiple domains induces an increase in sample efficiency of up to 70\% while maintaining the overall success rate of the MTRL agent.
Current multi-task reinforcement learning (MTRL) methods have the ability to perform a large number of tasks with a single policy. However w… (see more)hen attempting to interact with a new domain, the MTRL agent would need to be re-trained due to differences in domain dynamics and structure. Because of these limitations, we are forced to train multiple policies even though tasks may have shared dynamics, leading to needing more samples and is thus sample inefficient. In this work, we explore the ability of MTRL agents to learn in various domains with various dynamics by simultaneously learning in multiple domains, without the need to fine-tune extra policies. In doing so we find that a MTRL agent trained in multiple domains induces an increase in sample efficiency of up to 70\% while maintaining the overall success rate of the MTRL agent.
