Fine-tuning is dismissed as not effective for model editing due to its poor
performance compared to more specialized methods. However, fine-tuning is
simple, agnostic to the architectural details of the model being edited, and
able to leverage ongoing advances in standard training methods (e.g., PEFT),
making it an appealing choice for a model editor. In this work, we show that
pure fine-tuning can be a viable approach to model editing. We propose a slight
modification of naive fine-tuning with two key ingredients. First, we optimize
the conditional likelihood rather than the full likelihood. Second, we augment
the data with random paraphrases and facts to encourage generalization and
locality. Our experiments on ZsRE and CounterFact show that this simple
modification allows fine-tuning to often match or outperform specialized
editors in the edit score.

通过两个关键改进（优化条件似然和数据增强），研究表明纯粹的微调在模型编辑中是可行的，并经常能够与专门的编辑器达到或超过编辑分数。

纯微调的模型编辑

Model Editing by Pure Fine-Tuning

Zero-Shot Learning (ZSL) aims at classifying unlabeled objects by leveraging
auxiliary knowledge, such as semantic representations. A limitation of previous
approaches is that only intrinsic properties of objects, e.g. their visual
appearance, are taken into account while their context, e.g. the surrounding
objects in the image, is ignored. Following the intuitive principle that
objects tend to be found in certain contexts but not others, we propose a new
and challenging approach, context-aware ZSL, that leverages semantic
representations in a new way to model the conditional likelihood of an object
to appear in a given context. Finally, through extensive experiments conducted
on Visual Genome, we show that contextual information can substantially improve
the standard ZSL approach and is robust to unbalanced classes.

本文提出了一种基于语义表示的全新的 Zero-Shot Learning 方法，并引入了上下文因素提高了对象的分类效果，通过在 Visual Genome 上进行的实验表明，增加上下文信息可以显著提高标准的 ZSL 方法。

面向上下文的零样本学习用于物体识别

Context-Aware Zero-Shot Learning for Object Recognition

This paper compares two different ways of estimating statistical language
models. Many statistical NLP tagging and parsing models are estimated by
maximizing the (joint) likelihood of the fully-observed training data. However,
since these applications only require the conditional probability
distributions, these distributions can in principle be learnt by maximizing the
conditional likelihood of the training data. Perhaps somewhat surprisingly,
models estimated by maximizing the joint were superior to models estimated by
maximizing the conditional, even though some of the latter models intuitively
had access to ``more information''.

本文比较了两种不同的统计语言模型估计方式，发现通过最大化完全观测训练数据的 (联合) 似然来估计的模型优于通过最大化训练数据的条件似然来估计的模型。