Large Language Models (LLMs) are powerful models for generation tasks, but
they may not generate good quality outputs in their first attempt. Apart from
model fine-tuning, existing approaches to improve prediction accuracy and
quality typically involve LLM self-improvement / self-reflection that
incorporate feedback from models themselves. Despite their effectiveness, these
methods are hindered by their high computational cost and lack of scalability.
In this work, we propose CERET, a method for refining text generations by
considering semantic stability, entailment and inter-sample uncertainty
measures. Experimental results show that CERET outperforms Self-consistency and
Self-rerank baselines consistently under various task setups, by ~1.6% in
Rouge-1 for abstractive summarization and ~3.5% in hit rate for question
answering. Compared to LLM Self-rerank method, our approach only requires 9.4%
of its latency and is more cost-effective.

通过考虑语义稳定性、蕴涵和样本间不确定度的方法，我们提出了 CERET，以改进文本生成的质量，实验结果表明 CERET 在各种任务设置下持续优于其他方法，相对于 LLM 自排方法，我们的方法仅需其延迟的 9.4% 且更具成本效益。

CERET: 文本生成的经济外部修正

CERET: Cost-Effective Extrinsic Refinement for Text Generation

Model editing has emerged as a cost-effective strategy to update knowledge
stored in language models. However, model editing can have unintended
consequences after edits are applied: information unrelated to the edits can
also be changed, and other general behaviors of the model can be wrongly
altered. In this work, we investigate how model editing methods unexpectedly
amplify model biases post-edit. We introduce a novel benchmark dataset,
Seesaw-CF, for measuring bias-related harms of model editing and conduct the
first in-depth investigation of how different weight-editing methods impact
model bias. Specifically, we focus on biases with respect to demographic
attributes such as race, geographic origin, and gender, as well as qualitative
flaws in long-form texts generated by edited language models. We find that
edited models exhibit, to various degrees, more biased behavior as they become
less confident in attributes for Asian, African, and South American subjects.
Furthermore, edited models amplify sexism and xenophobia in text generations
while remaining seemingly coherent and logical. Finally, editing facts about
place of birth, country of citizenship, or gender have particularly negative
effects on the model's knowledge about unrelated features like field of work.

模型编辑是一种成本效益高的策略，用于更新存储在语言模型中的知识。然而，模型编辑可能在应用编辑后产生意想不到的后果：与编辑无关的信息也可能被改变，并且模型的其他一般行为也可能被错误地改变。本研究调查了模型编辑方法如何意外地放大模型的偏见，并引入了一个新的基准数据集 Seesaw-CF，用于衡量模型编辑对偏见相关伤害的影响，并对不同的权重编辑方法如何影响模型偏见进行了全面调查。具体地，我们关注与种族、地理起源和性别等人口属性相关的偏见，以及经过编辑的语言模型生成的长篇文本的定性缺陷。我们发现，经过编辑的模型在对亚洲、非洲和南美洲等对象的属性越不自信时，更倾向于表现出不同程度的偏见行为。此外，经过编辑的模型在生成文本时放大了性别歧视和排外情绪，同时仍然表现得似乎连贯且合乎逻辑。最后，编辑关于出生地、公民国籍或性别的事实对模型对类似职业的不相关特征的了解产生特别负面影响。