LaSQuE: Improved Zero-Shot Classification from Explanations Through Quantifier Modeling and Curriculum Learning
A hallmark of human intelligence is the ability to learn new concepts purely from language. Several recent approaches have explored training machine learning models via natural language supervision. However, these approaches fall short in leveraging linguistic quantifiers (such as 'always' or 'rarely') and mimicking humans in compositionally learning complex tasks. Here, we present LaSQuE, a method that can learn zero-shot classifiers from language explanations by using three new strategies - (1) modeling the semantics of linguistic quantifiers in explanations (including exploiting ordinal strength relationships, such as 'always' > 'likely'), (2) aggregating information from multiple explanations using an attention-based mechanism, and (3) model training via curriculum learning. With these strategies, LaSQuE outperforms prior work, showing an absolute gain of up to 7% in generalizing to unseen real-world classification tasks.
Code (0)
등록된 구현이 없습니다.
Tasks
zero-shot-classificationZero-Shot LearningSimilar Papers 제목 키워드 기반
Zero-Shot Classification by Logical Reasoning on Natural Language Explanations
Humans can classify data of an unseen category by reasoning on its language explanations. This ability is owing to the compositional nature of language: we can combine previously seen attributes to describe the new categ…
ClassificationLogical Reasoningzero-shot-classificationZero-Shot LearningThe Effect of Model Size on LLM Post-hoc Explainability via LIME
Large language models (LLMs) are becoming bigger to boost performance. However, little is known about how explainability is affected by this trend. This work explores LIME explanations for DeBERTaV3 models of four differ…
Natural Language Inferencezero-shot-classificationZero-Shot LearningInterpreting and Analysing CLIP's Zero-Shot Image Classification via Mutual Knowledge
Contrastive Language-Image Pretraining (CLIP) performs zero-shot image classification by mapping images and textual class representation into a shared embedding space, then retrieving the class closest to the image. This…
Classificationimage-classificationImage Classificationzero-shot-classification+2Improving Few-Shot Image Classification Using Machine- and User-Generated Natural Language Descriptions
Humans can obtain the knowledge of novel visual concepts from language descriptions, and we thus use the few-shot image classification task to investigate whether a machine learning model can have this capability. Our pr…
DecoderFew-Shot Image Classificationimage-classificationImage ClassificationLarge Language Models Are Better Logical Fallacy Reasoners with Counterargument, Explanation, and Goal-Aware Prompt Formulation
The advancement of Large Language Models (LLMs) has greatly improved our ability to process complex language. However, accurately detecting logical fallacies remains a significant challenge. This study presents a novel a…
Logical FallaciesLogical Fallacy Detection