Related papers: Assertion Enhanced Few-Shot Learning: Instructive …

Large language models have recently been shown to attain reasonable zero-shot generalization on a diverse set of tasks (Brown et al., 2020). It has been hypothesized that this is a consequence of implicit multitask learning in language…

Recent work has demonstrated the promise of combining local explanations with active learning for understanding and supervising black-box models. Here we show that, under specific conditions, these algorithms may misrepresent the quality of…

We equip a smaller Language Model to generalise to answering challenging compositional questions that have not been seen in training. To do so we propose a combination of multitask supervised pretraining on up to 93 tasks designed to…

Owing to the capability of in-context learning, large language models (LLMs) have shown impressive performance across diverse mathematical reasoning benchmarks. However, we find that few-shot demonstrations can sometimes bring negative…

Many real world learning tasks involve complex or hard-to-specify objectives, and using an easier-to-specify proxy can lead to poor performance or misaligned behavior. One solution is to have humans provide a training signal by…

In recent years, the generation of conversation content based on deep neural networks has attracted many researchers. However, traditional neural language models tend to generate general replies, lacking logical and emotional factors. This…

Knowledge distillation is a promising approach to transfer capabilities from complex teacher models to smaller, resource-efficient student models that can be deployed easily, particularly in task-aware scenarios. However, existing methods…

Scaling up visual category recognition to large numbers of classes remains challenging. A promising research direction is zero-shot learning, which does not require any training data to recognize new classes, but rather relies on some form…

Integrating free-text explanations to in-context learning of large language models (LLM) is shown to elicit strong reasoning capabilities along with reasonable explanations. In this paper, we consider the problem of leveraging the…

One-on-one tutoring is an effective instructional method for enhancing learning, yet its efficacy hinges on tutor competencies. Novice math tutors often prioritize content-specific guidance, neglecting aspects such as social-emotional…

Learning to converse using only a few examples is a great challenge in conversational AI. The current best conversational models, which are either good chit-chatters (e.g., BlenderBot) or goal-oriented systems (e.g., MinTL), are language…

Attention mechanisms have demonstrated significant potential in enhancing learning models by identifying key portions of input data, particularly in scenarios with limited training samples. Inspired by human perception, we propose that…

As the labeling cost for different modules in task-oriented dialog (ToD) systems is expensive, a major challenge is to train different modules with the least amount of labeled data. Recently, large-scale pre-trained language models, have…

Large language models have the potential to generate explanations for their own predictions in a variety of styles based on user instructions. Recent research has examined whether these self-explanations faithfully reflect the models'…

Many capable large language models (LLMs) are developed via self-supervised pre-training followed by a reinforcement-learning fine-tuning phase, often based on human or AI feedback. During this stage, models may be guided by their inductive…

Prevailing methods for mapping large generative language models to supervised tasks may fail to sufficiently probe models' novel capabilities. Using GPT-3 as a case study, we show that 0-shot prompts can significantly outperform few-shot…

Natural language (NL) explanations of model predictions are gaining popularity as a means to understand and verify decisions made by large black-box pre-trained models, for NLP tasks such as Question Answering (QA) and Fact Verification.…

Few-Shot Relation Extraction aims at predicting the relation for a pair of entities in a sentence by training with a few labelled examples in each relation. Some recent works have introduced relation information (i.e., relation labels or…

Large language models have shown impressive few-shot results on a wide range of tasks. However, when knowledge is key for such results, as is the case for tasks such as question answering and fact checking, massive parameter counts to store…

A key aspect of alignment is the proper use of within-document evidence to construct document-level decisions. We analyze the relationship between the retrieval and interpretation of within-document evidence for large language model in a…