paper-with-me

홈 › Papers

CURIE: An Iterative Querying Approach for Reasoning About Situations

2021-04-01 · CSRR (ACL) 2022 5 · Dheeraj Rajagopal, Aman Madaan, Niket Tandon, Yiming Yang, Shrimai Prabhumoye, Abhilasha Ravichander, Peter Clark, Eduard Hovy

Recently, models have been shown to predict the effects of unexpected situations, e.g., would cloudy skies help or hinder plant growth? Given a context, the goal of such situational reasoning is to elicit the consequences of a new situation (st) that arises in that context. We propose a method to iteratively build a graph of relevant consequences explicitly in a structured situational graph (st-graph) using natural language queries over a finetuned language model (M). Across multiple domains, CURIE generates st-graphs that humans find relevant and meaningful in eliciting the consequences of a new situation. We show that st-graphs generated by CURIE improve a situational reasoning end task (WIQA-QA) by 3 points on accuracy by simply augmenting their input with our generated situational graphs, especially for a hard subset that requires background knowledge and multi-hop reasoning.

📄 PDF Abstract BibTeX arXiv:2104.00814

Code (1)

dheerajrajagopal/EIGEN pytorch

Tasks

Language ModelingLanguage ModellingNatural Language Queries

Similar Papers 제목 키워드 기반

CURIE: Evaluating LLMs On Multitask Scientific Long Context Understanding and Reasoning

2025-03-14 · HAO CUI, Zahra Shamsi, Gowoon Cheon, Xuejian Ma 외

Scientific problem-solving involves synthesizing information while applying expert knowledge. We introduce CURIE, a scientific long-Context Understanding,Reasoning and Information Extraction benchmark to measure the pote…

Long-Context Understanding

Improving Neural Model Performance through Natural Language Feedback on Their Explanations

2021-04-18 · Aman Madaan, Niket Tandon, Dheeraj Rajagopal, Yiming Yang 외

A class of explainable NLP models for reasoning tasks support their decisions by generating free-form or structured explanations, but what happens when these supporting structures contain errors? Our goal is to allow use…

Curie: Toward Rigorous and Automated Scientific Experimentation with AI Agents

2025-02-22 · Patrick Tser Jern Kon, Jiachen Liu, Qiuyi Ding, Yiming Qiu 외

Scientific experimentation, a cornerstone of human progress, demands rigor in reliability, methodical control, and interpretability to yield meaningful results. Despite the growing capabilities of large language models (…

AI Agent

Complex Query Answering on Eventuality Knowledge Graph with Implicit Logical Constraints

2023-05-30 · NeurIPS 2023 11 · Jiaxin Bai, Xin Liu, Weiqi Wang, Chen Luo 외

Querying knowledge graphs (KGs) using deep learning approaches can naturally leverage the reasoning and generalization ability to learn to infer better answers. Traditional neural complex query answering (CQA) approaches…

Complex Query AnsweringKnowledge Graphs

UNcommonsense Reasoning: Abductive Reasoning about Uncommon Situations

2023-11-14 · Wenting Zhao, Justin T Chiu, Jena D. Hwang, Faeze Brahman 외

Language technologies that accurately model the dynamics of events must perform commonsense reasoning. Existing work evaluating commonsense reasoning focuses on making inferences about common, everyday situations. To ins…

DiversityImitation LearningSpecificity