Related papers: Model Editing with Canonical Examples

Effective lesson planning is crucial in education process, serving as the cornerstone for high-quality teaching and the cultivation of a conducive learning atmosphere. This study investigates how large language models (LLMs) can enhance…

We present Backpacks: a new neural architecture that marries strong modeling performance with an interface for interpretability and control. Backpacks learn multiple non-contextual sense vectors for each word in a vocabulary, and represent…

The current trend to improve language model performance seems to be based on scaling up with the number of parameters (e.g. the state of the art GPT4 model has approximately 1.7 trillion parameters) or the amount of training data fed into…

Argument mining is a subfield of argumentation that aims to automatically extract argumentative structures and their relations from natural language texts. This paper investigates how a single large language model can be leveraged to…

Although rarely stated, in practice, Grammatical Error Correction (GEC) encompasses various models with distinct objectives, ranging from grammatical error detection to improving fluency. Traditional evaluation methods fail to fully capture…

Language Models are the underpin of all modern Natural Language Processing (NLP) tasks. The introduction of the Transformers architecture has contributed significantly into making Language Modeling very effective across many NLP task,…

Language models (LMs) with less than 100B parameters are known to perform poorly on chain-of-thought (CoT) reasoning in contrast to large LMs when solving unseen tasks. In this work, we aim to equip smaller LMs with the step-by-step…

We introduce a new setting, Edit Transfer, where a model learns a transformation from just a single source-target example and applies it to a new query image. While text-based methods excel at semantic manipulations through textual prompts,…

Much of the success of modern language models depends on finding a suitable prompt to instruct the model. Until now, it has been largely unknown how variations in the linguistic expression of prompts affect these models. This study…

Humans often become more self-aware under threat, yet can lose self-awareness when absorbed in a task; we hypothesize that language models exhibit environment-dependent \textit{evaluation awareness}. This raises concerns that models could…

Current approaches for fixing systematic problems in NLP models (e.g. regex patches, finetuning on more data) are either brittle, or labor-intensive and liable to shortcuts. In contrast, humans often provide corrections to each other…

We consider the model selection task in the stochastic contextual bandit setting. Suppose we are given a collection of base contextual bandit algorithms. We provide a master algorithm that combines them and achieves the same performance, up…

We present the surprising finding that a language model's reasoning capabilities can be improved by training on synthetic datasets of chain-of-thought (CoT) traces from more capable models, even when all of those traces lead to an incorrect…

Large language models (LLMs) exhibit cognitive biases -- systematic tendencies of irrational decision-making, similar to those seen in humans. Prior work has found that these biases vary across models and can be amplified by instruction…

Fine-tuning pre-trained language models (LMs) is essential for enhancing their capabilities. Existing techniques commonly fine-tune on input-output pairs (e.g., instruction tuning) or with numerical rewards that gauge the output quality…

When scaled to hundreds of billions of parameters, pretrained language models such as GPT-3 (Brown et al., 2020) achieve remarkable few-shot performance. However, enormous amounts of compute are required for training and applying such big…

How should two language models interact to produce better code than either can alone? The conventional approach -- a reasoning model plans, a code specialist implements -- seems natural but fails: on HumanEval+, plan-then-code degrades…

Current large language models can perform reasonably well on complex tasks that require step-by-step reasoning with few-shot learning. Are these models applying reasoning skills they have learnt during pre-training and reason outside of…

Popular Neural Machine Translation model training uses strategies like backtranslation to improve BLEU scores, requiring large amounts of additional data and training. We introduce a class of conditional generative-discriminative hybrid…

Prompting language models (LMs) with training examples and task descriptions has been seen as critical to recent successes in few-shot learning. In this work, we show that finetuning LMs in the few-shot setting can considerably reduce the…