Related papers: Instruction Tuning Chronologically Consistent Lang…
Features in machine learning problems are often time-varying and may be related to outputs in an algebraic or dynamical manner. The dynamic nature of these machine learning problems renders current higher order accelerated gradient descent…
Instruction following is a critical ability for Large Language Models to perform downstream tasks. The standard approach to instruction tuning has relied on a specific phase of supervised fine-tuning over curated instruction datasets,…
Large language models may encode sensitive information or outdated knowledge that needs to be removed, to ensure responsible and compliant model responses. Unlearning has emerged as an efficient alternative to full retraining, aiming to…
We present a scalable method to build a high quality instruction following language model by automatically labelling human-written text with corresponding instructions. Our approach, named instruction backtranslation, starts with a language…
Instruction tuning enhances large language models (LLMs) to follow human instructions across diverse tasks, relying on high-quality datasets to guide behavior. However, these datasets, whether manually curated or synthetically generated,…
A fundamental requirement for intelligent systems is the ability to learn continuously under changing environments. However, models trained in this regime often suffer from catastrophic forgetting. Leveraging pre-trained models has recently…
When used in complex engineered systems, such as communication networks, artificial intelligence (AI) models should be not only as accurate as possible, but also well calibrated. A well-calibrated AI model is one that can reliably quantify…
Pre-trained Language Models (LMs) exhibit strong zero-shot and in-context learning capabilities; however, their behaviors are often difficult to control. By utilizing Reinforcement Learning from Human Feedback (RLHF), it is possible to…
Most classroom engagements with generative AI focus on prompting pre-trained models, leaving the role of training data and model mechanics opaque. We developed a browser-based tool that allows students to train a small transformer language…
Aligning language models (LMs) with user intent is becoming increasingly relevant to enhance user experience. This calls for designing methods that can allow users to control the properties of the language that LMs generate, for example,…
This work introduces EE-Tuning, a lightweight and economical solution to training/tuning early-exit large language models (LLMs). In contrast to the common approach of full-parameter pre-training, EE-Tuning augments any pre-trained (and…
Most large language models are fine-tuned using either expensive human-annotated data or GPT-4 generated data which cannot guarantee performance in certain domains. We argue that although the web-crawled data often has formatting errors…
Foundation models have recently gained attention within the field of machine learning thanks to its efficiency in broad data processing. While researchers had attempted to extend this success to time series models, the main challenge is…
Many facts come with an expiration date, from the name of the President to the basketball team Lebron James plays for. But language models (LMs) are trained on snapshots of data collected at a specific moment in time, and this can limit…
Instruction tuning aligns the response of large language models (LLMs) with human preferences. Despite such efforts in human--LLM alignment, we find that instruction tuning does not always make LLMs human-like from a cognitive modeling…
A trustworthy real-world prediction system should produce well-calibrated confidence scores; that is, its confidence in an answer should be indicative of the likelihood that the answer is correct, enabling deferral to an expert in cases of…
We introduce a simple yet powerful framework for training large language models. In contrast to the standard autoregressive next-token prediction based on an exact prefix, we propose a perturbation-based procedure that first transforms the…
Learning to associate audio with textual descriptions is valuable for a range of tasks, including pretraining, zero-shot classification, audio retrieval, audio captioning, and text-conditioned audio generation. Existing contrastive…
Time series forecasting traditionally relies on unimodal numerical inputs, which often struggle to capture high-level semantic patterns due to their dense and unstructured nature. While recent approaches have explored representing time…
Large language models (LLMs) are increasingly used in finance and economics, where prompt-based attempts against look-ahead bias implicitly assume that models understand chronology. We test this fundamental question with a series of…