Vaiva Imbrasaite — accepted AI-conference papers

2024

TaskLAMA: Probing the Complex Task Understanding of Language Models

Quan Yuan, Mehran Kazemi, Xin Xu, Isaac Noble, Vaiva Imbrasaite, Deepak Ramachandran

AAAI 2024technical

Structured Complex Task Decomposition (SCTD) is the problem of breaking down a complex real-world task (such as planning a wedding) into a directed acyclic graph over individual steps that contribute to achieving the task, with edges specifying temporal dependencies between steps. SCTD is an i…

Cited by 8 Source ↗PDF ↗Scholar ↗

2023

BoardgameQA: A Dataset for Natural Language Reasoning with Contradictory Information

Mehran Kazemi, Quan Yuan, Deepti Bhatia, Najoung Kim, Xin Xu, Vaiva Imbrasaite +1

NeurIPS 2023poster

Automated reasoning with unstructured natural text is a key requirement for many potential applications of NLP and for developing robust AI systems. Recently, Language Models (LMs) have demonstrated complex reasoning capacities even without any finetuning. However, existing evaluation for automated…

Cited by 39 Source ↗PDF ↗Scholar ↗