Chain of Condition: Construct, Verify and Solve Conditions for Conditional Question Answering

• URL: http://arxiv.org/abs/2408.05442v2
• Date: Fri, 4 Oct 2024 03:13:41 GMT
• Title: Chain of Condition: Construct, Verify and Solve Conditions for Conditional Question Answering
• Authors: Jiuheng Lin, Yuxuan Lai, Yansong Feng,
• Abstract summary: Conditional question answering (CQA) is an important task that aims to find probable answers and identify missing conditions. Existing approaches struggle with CQA due to two challenges: (1) precisely identifying necessary conditions and the logical relationship, and (2) verifying conditions to detect any that are missing. We propose a novel prompting approach, Chain of condition, by first identifying all conditions and constructing their logical relationships explicitly according to the document.
• Score: 34.599299893060895
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Conditional question answering (CQA) is an important task that aims to find probable answers and identify missing conditions. Existing approaches struggle with CQA due to two challenges: (1) precisely identifying necessary conditions and the logical relationship, and (2) verifying conditions to detect any that are missing. In this paper, we propose a novel prompting approach, Chain of condition, by first identifying all conditions and constructing their logical relationships explicitly according to the document, then verifying whether these conditions are satisfied, finally solving the logical expression to indicate any missing conditions and generating the answer accordingly. Experiments on two CQA benchmark datasets show our chain of condition outperforms existing prompting baselines, establishing a new state of the art. Furthermore, with only a few examples, our method can facilitate GPT-3.5-Turbo or GPT-4 to outperform all existing supervised models.

Related papers

• FREST: Feature RESToration for Semantic Segmentation under Multiple Adverse Conditions [35.243694861973715]
  FREST is a novel feature restoration framework for source-free domain adaptation (SFDA) of semantic segmentation to adverse conditions. FREST achieves a state of the art on two public benchmarks for SFDA to adverse conditions. It shows superior generalization ability on unseen datasets.
  arXiv  Detail & Related papers  (2024-07-18T12:07:02Z)
• MDCR: A Dataset for Multi-Document Conditional Reasoning [20.42067697305166]
  ConditionalQA was proposed to evaluate models' capability of reading a document and answering eligibility questions, considering unmentioned conditions. We propose a new dataset MDCR, which can reflect real-world challenges and serve as a new test bed for complex conditional reasoning that requires optimization.
  arXiv  Detail & Related papers  (2024-06-17T17:38:43Z)
• SQ Lower Bounds for Non-Gaussian Component Analysis with Weaker Assumptions [50.20087216230159]
  We study the complexity of Non-Gaussian Component Analysis (NGCA) in the Statistical Query model. We prove near-optimal SQ lower bounds for NGCA under the moment-matching condition only.
  arXiv  Detail & Related papers  (2024-03-07T18:49:32Z)
• Reasoning over Logically Interacted Conditions for Question Answering [113.9231035680578]
  We study a more challenging task where answers are constrained by a list of conditions that logically interact. We propose a new model, TReasoner, for this challenging reasoning task. TReasoner achieves state-of-the-art performance on two benchmark conditional QA datasets.
  arXiv  Detail & Related papers  (2022-05-25T16:41:39Z)
• ConditionalQA: A Complex Reading Comprehension Dataset with Conditional Answers [93.55268936974971]
  We describe a Question Answering dataset that contains complex questions with conditional answers. We call this dataset ConditionalQA. We show that ConditionalQA is challenging for many of the existing QA models, especially in selecting answer conditions.
  arXiv  Detail & Related papers  (2021-10-13T17:16:46Z)
• Learning Causal Relationships from Conditional Moment Conditions by Importance Weighting [11.326695040991192]
  We consider learning causal relationships under conditional moment conditions. conditional moment conditions pose serious challenges for causal inference in high-dimensional settings. We propose a method that transforms conditional moment conditions to unconditional moment conditions.
  arXiv  Detail & Related papers  (2021-08-03T06:07:07Z)
• Generating Diverse and Consistent QA pairs from Contexts with Information-Maximizing Hierarchical Conditional VAEs [62.71505254770827]
  We propose a conditional variational autoencoder (HCVAE) for generating QA pairs given unstructured texts as contexts. Our model obtains impressive performance gains over all baselines on both tasks, using only a fraction of data for training.
  arXiv  Detail & Related papers  (2020-05-28T08:26:06Z)
• Conditional Self-Attention for Query-based Summarization [49.616774159367516]
  We propose textitconditional self-attention (CSA), a neural network module designed for conditional dependency modeling. Experiments on Debatepedia and HotpotQA benchmark datasets show CSA consistently outperforms vanilla Transformer.
  arXiv  Detail & Related papers  (2020-02-18T02:22:31Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.