SOTAVerified

Multi-hop Question Answering

Papers

Showing 2650 of 202 papers

TitleStatusHype
PokeMQA: Programmable knowledge editing for Multi-hop Question AnsweringCode1
Reasoning over Public and Private Data in Retrieval-Based SystemsCode1
Re-ReST: Reflection-Reinforced Self-Training for Language AgentsCode1
Collab-RAG: Boosting Retrieval-Augmented Generation for Complex Question Answering via White-Box and Black-Box LLM CollaborationCode1
HybridQA: A Dataset of Multi-Hop Question Answering over Tabular and Textual DataCode1
Answering Questions by Meta-Reasoning over Multiple Chains of ThoughtCode1
Improving Embedded Knowledge Graph Multi-hop Question Answering by introducing Relational Chain ReasoningCode1
Avoiding Reasoning Shortcuts: Adversarial Evaluation, Training, and Model Development for Multi-Hop QACode1
Constructing A Multi-hop QA Dataset for Comprehensive Evaluation of Reasoning StepsCode1
Grounded Multi-Hop VideoQA in Long-Form Egocentric VideosCode1
HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question AnsweringCode1
DeepEdit: Knowledge Editing as Decoding with ConstraintsCode1
Direct Evaluation of Chain-of-Thought in Multi-hop Reasoning with Knowledge GraphsCode1
CompAct: Compressing Retrieved Documents Actively for Question AnsweringCode1
Hierarchical Retrieval-Augmented Generation Model with Rethink for Multi-hop Question AnsweringCode1
End-to-End Beam Retrieval for Multi-Hop Question AnsweringCode1
KITLM: Domain-Specific Knowledge InTegration into Language Models for Question AnsweringCode1
Enhancing Multi-modal and Multi-hop Question Answering via Structured Knowledge and Unified Retrieval-GenerationCode1
Learning From Failure: Integrating Negative Examples when Fine-tuning Large Language Models as AgentsCode1
HopWeaver: Synthesizing Authentic Multi-Hop Questions Across Text CorporaCode1
Dynamic Semantic Graph Construction and Reasoning for Explainable Multi-hop Science Question AnsweringCode1
Analyzing the Effectiveness of the Underlying Reasoning Tasks in Multi-hop Question AnsweringCode1
MQuAKE: Assessing Knowledge Editing in Language Models via Multi-Hop QuestionsCode1
Improving Multi-hop Question Answering over Knowledge Graphs using Knowledge Base EmbeddingsCode1
Search-in-the-Chain: Interactively Enhancing Large Language Models with Search for Knowledge-intensive TasksCode1
Show:102550
← PrevPage 2 of 9Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1Multi-hop Dense Passage Retriever (MDR)Answer F156.5Unverified
#ModelMetricClaimedVerifiedStatus
1Beam RetrievalAn69.2Unverified