no code implementations • 6 Feb 2024 • Soumya Sanyal, Tianyi Xiao, Jiacheng Liu, Wenya Wang, Xiang Ren
Finally, we use this model to filter out inconsistent model-generated rationales in self-consistency decoding, resulting in a 6% accuracy improvement on average across three MCQ datasets.
no code implementations • 16 Nov 2023 • Ziyi Liu, Isabelle Lee, Yongkang Du, Soumya Sanyal, Jieyu Zhao
In a plethora of recent work, large language models (LLMs) demonstrated impressive reasoning ability, but many proposed downstream reasoning tasks focus on performance-wise evaluation.
1 code implementation • 31 May 2023 • Faeze Brahman, Chandra Bhagavatula, Valentina Pyatkin, Jena D. Hwang, Xiang Lorraine Li, Hirona J. Arai, Soumya Sanyal, Keisuke Sakaguchi, Xiang Ren, Yejin Choi
In addition, we introduce a novel task, Counterfactual Planning, that requires a revision of a plan to cope with a counterfactual situation.
1 code implementation • NeurIPS 2023 • Nouha Dziri, Ximing Lu, Melanie Sclar, Xiang Lorraine Li, Liwei Jiang, Bill Yuchen Lin, Peter West, Chandra Bhagavatula, Ronan Le Bras, Jena D. Hwang, Soumya Sanyal, Sean Welleck, Xiang Ren, Allyson Ettinger, Zaid Harchaoui, Yejin Choi
We formulate compositional tasks as computation graphs to systematically quantify the level of complexity, and break down reasoning steps into intermediate sub-procedures.
no code implementations • 19 Dec 2022 • Soumya Sanyal, Yichong Xu, Shuohang Wang, ZiYi Yang, Reid Pryzant, Wenhao Yu, Chenguang Zhu, Xiang Ren
Logical reasoning of text is an important ability that requires understanding the information present in the text, their interconnections, and then reasoning through them to infer new conclusions.
1 code implementation • 21 Sep 2022 • Wenhao Yu, Dan Iter, Shuohang Wang, Yichong Xu, Mingxuan Ju, Soumya Sanyal, Chenguang Zhu, Michael Zeng, Meng Jiang
We call our method generate-then-read (GenRead), which first prompts a large language model to generate contextutal documents based on a given question, and then reads the generated documents to produce the final answer.
1 code implementation • 25 May 2022 • Soumya Sanyal, Zeyi Liao, Xiang Ren
Transformers have been shown to be able to perform deductive reasoning on a logical rulebase containing rules and statements written in English natural language.
1 code implementation • ACL 2022 • Soumya Sanyal, Harman Singh, Xiang Ren
Recent works show that such models can also produce the reasoning steps (i. e., the proof graph) that emulate the model's logical reasoning process.
2 code implementations • EMNLP 2021 • Soumya Sanyal, Xiang Ren
As a prominent attribution-based explanation algorithm, Integrated Gradients (IG) is widely adopted due to its desirable explanation axioms and the ease of gradient computation.
1 code implementation • NeurIPS 2021 • Aaron Chan, Jiashu Xu, Boyuan Long, Soumya Sanyal, Tanishq Gupta, Xiang Ren
and fine (Which nodes/paths in the KG are useful?)
1 code implementation • 18 Nov 2019 • Ekagra Ranjan, Soumya Sanyal, Partha Pratim Talukdar
Graph Neural Networks (GNN) have been shown to work effectively for modeling graph structured data to solve tasks such as node classification, link prediction and graph classification.
Ranked #3 on Graph Classification on FRANKENSTEIN
2 code implementations • ACL 2020 • Zhiqing Sun, Shikhar Vashishth, Soumya Sanyal, Partha Talukdar, Yiming Yang
Knowledge Graph Completion (KGC) aims at automatically predicting missing links for large-scale knowledge graphs.
Ranked #25 on Link Prediction on FB15k-237 (MR metric)
4 code implementations • ICLR 2020 • Shikhar Vashishth, Soumya Sanyal, Vikram Nitin, Partha Talukdar
Multi-relational graphs are a more general and prevalent form of graphs where each edge has a label and direction associated with it.
Ranked #22 on Link Prediction on FB15k-237
1 code implementation • 1 Nov 2019 • Shikhar Vashishth, Soumya Sanyal, Vikram Nitin, Nilesh Agrawal, Partha Talukdar
In this paper, we analyze how increasing the number of these interactions affects link prediction performance, and utilize our observations to propose InteractE.
Ranked #11 on Link Prediction on YAGO3-10
1 code implementation • 14 Nov 2018 • Soumya Sanyal, Janakiraman Balachandran, Naganand Yadati, Abhishek Kumar, Padmini Rajagopalan, Suchismita Sanyal, Partha Talukdar
Some of the major challenges involved in developing such models are, (i) limited availability of materials data as compared to other fields, (ii) lack of universal descriptor of materials to predict its various properties.
Ranked #4 on Band Gap on Materials Project