ALERT: Adapt Language Models to Reasoning Tasks

By Ping Yu, Tianlu Wang, O. Yu. Golovneva, Badr AlKhamissi, Gargi Ghosh, Mona T. Diab, Asli Celikyilmaz. 2022

20 citations recorded by the source corpus.

Recent advancements in large language models have enabled them to perform well on complex tasks that require step-by-step reasoning with few-shot learning. However, it is unclear whether these models are applying reasoning skills they have learnt during pre-training , or if they are simply memorizing their training corpus at finer granularity and have learnt to better understand their context.To address this question, we introduce {pasted macro ‘OUR’}model, a benchmark and suite of analyses for evaluating reasoning skills of language models. {pasted macro ‘OUR’}model enables comparing pre-trained and finetuned models on complex tasks that require reasoning skills to solve. Our benchmark provides a test bed to asses any language model on fine-grained reasoning skills, which spans over 20 datasets and covers 10 different reasoning skills. By using {pasted macro ‘OUR’}model we further investigate the role of finetuning. Our extensive empirical analysis shows that language models learn more reasoning skills such as textual entailment, abductive reasoning, and analogical reasoning during the finetuning stage compared to pretraining stage. However, we also find that when language models are finetuned they tend to overfit to the prompt template, which hurts the robustness of models causing generalization problems.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Large Language Models, Prompting & Reasoning

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

In Large Language Models

In Prompting & Reasoning

Citations in the corpus

Augmented Language Models: a Survey (2023, background): “To what extent LMs actually use the stated reasoning steps to support the final prediction remains poorly understood (Yu et al., 2022).”
Reasoning with Language Model is Planning with World Model (2023, background): “For example, in creating action plans to move blocks to a target state, GPT-3 [5] achieves a success rate of only 1%, compared to 78% for humans [57]; these models also struggle when solving complex tasks that require multiple steps of math, logical, or commonsense reasoning [65, 22, 41, 6].”