Progressive-hint prompting improves reasoning in large language models
The performance of Large Language Models (LLMs) in reasoning tasks depends heavily on
prompt design, with Chain-of-Thought (CoT) and self-consistency being critical methods that …
prompt design, with Chain-of-Thought (CoT) and self-consistency being critical methods that …
Rationale-augmented ensembles in language models
Recent research has shown that rationales, or step-by-step chains of thought, can be used
to improve performance in multi-step reasoning tasks. We reconsider rationale-augmented …
to improve performance in multi-step reasoning tasks. We reconsider rationale-augmented …
Scienceworld: Is your agent smarter than a 5th grader?
We present ScienceWorld, a benchmark to test agents' scientific reasoning abilities in a new
interactive text environment at the level of a standard elementary school science curriculum …
interactive text environment at the level of a standard elementary school science curriculum …
Multi-hop question answering
Abstract The task of Question Answering (QA) has attracted significant research interest for a
long time. Its relevance to language understanding and knowledge retrieval tasks, along …
long time. Its relevance to language understanding and knowledge retrieval tasks, along …
Hierarchy-aware multi-hop question answering over knowledge graphs
Knowledge graphs (KGs) have been widely used to enhance complex question answering
(QA). To understand complex questions, existing studies employ language models (LMs) to …
(QA). To understand complex questions, existing studies employ language models (LMs) to …
Nonfactoid question answering as query-focused summarization with graph-enhanced multihop inference
Nonfactoid question answering (QA) is one of the most extensive yet challenging
applications and research areas in natural language processing (NLP). Existing methods fall …
applications and research areas in natural language processing (NLP). Existing methods fall …
Joint reasoning with knowledge subgraphs for Multiple Choice Question Answering
Humans are able to reason from multiple sources to arrive at the correct answer. In the
context of Multiple Choice Question Answering (MCQA), knowledge graphs can provide …
context of Multiple Choice Question Answering (MCQA), knowledge graphs can provide …
Unifying Text, Tables, and Images for Multimodal Question Answering
Multimodal question answering (MMQA), which aims to derive the answer from multiple
knowledge modalities (eg, text, tables, and images), has received increasing attention due …
knowledge modalities (eg, text, tables, and images), has received increasing attention due …
Hop, union, generate: Explainable multi-hop reasoning without rationale supervision
Explainable multi-hop question answering (QA) not only predicts answers but also identifies
rationales, ie subsets of input sentences used to derive the answers. This problem has been …
rationales, ie subsets of input sentences used to derive the answers. This problem has been …
Multi-hop question answering over incomplete knowledge graph with abstract conceptual evidence
Abstract Multi-hop Question Answering over Knowledge Graph (KGQA) aims to reason
answers through multiple triples in Knowledge Graphs (KGs). Unfortunately, in practice due …
answers through multiple triples in Knowledge Graphs (KGs). Unfortunately, in practice due …