Template Filling for Controllable Commonsense Reasoning
Large-scale sequence-to-sequence models have shown to be adept at both multiple-choice and open-domain commonsense reasoning tasks. However, the current systems do not provide the ability to control the various attributes of the reasoning chain. To enable better controllability, we propose to study the commonsense reasoning as a template filling task (TemplateCSR) -- where the language models fills reasoning templates with the given constraints as control factors. As an approach to TemplateCSR, we (i) propose a dataset of commonsense reasoning template-expansion pairs and (ii) introduce POTTER, a pretrained sequence-to-sequence model using prompts to perform commonsense reasoning across concepts. Our experiments show that our approach outperforms baselines both in generation metrics and factuality metrics. We also present a detailed error analysis on our approach's ability to reliably perform commonsense reasoning.
Code (0)
등록된 구현이 없습니다.
Tasks
Multiple-choiceSimilar Papers 제목 키워드 기반
A Dataset for Cross-Domain Reasoning via Template Filling
While several benchmarks exist for reasoning tasks, reasoning across domains is an under-explored area in NLP. Towards this, we present a dataset and a prompt-template-filling approach to enable sequence to sequence mode…
DecoderCORECODE: A Common Sense Annotated Dialogue Dataset with Benchmark Tasks for Chinese Large Language Models
As an indispensable ingredient of intelligence, commonsense reasoning is crucial for large language models (LLMs) in real-world scenarios. In this paper, we propose CORECODE, a dataset that contains abundant commonsense …
Causal InferenceCommon Sense ReasoningDesigning Templates for Eliciting Commonsense Knowledge from Pretrained Sequence-to-Sequence Models
While internalized {``}implicit knowledge{''} in pretrained transformers has led to fruitful progress in many natural language understanding tasks, how to most effectively elicit such knowledge remains an open question. …
Multiple-choiceNatural Language UnderstandingOpen-Ended Question AnsweringQuestion AnsweringCASPR: A Commonsense Reasoning-based Conversational Socialbot
We report on the design and development of the CASPR system, a socialbot designed to compete in the Amazon Alexa Socialbot Challenge 4. CASPR's distinguishing characteristic is that it will use automated commonsense reas…
PhilosophyUnlocking the Potential of Diffusion Language Models through Template Infilling
Diffusion Language Models (DLMs) have emerged as a promising alternative to Autoregressive Language Models, yet their inference strategies remain limited to prefix-based prompting inherited from the autoregressive paradi…
Mathematical ReasoningCode Generation