REVIEW 3 cited by
Multi-hop Reading Comprehension through Question Decomposition and Rescoring
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Multi-hop Reading Comprehension through Question Decomposition and Rescoring
read the original abstract
Multi-hop Reading Comprehension (RC) requires reasoning and aggregation across several paragraphs. We propose a system for multi-hop RC that decomposes a compositional question into simpler sub-questions that can be answered by off-the-shelf single-hop RC models. Since annotations for such decomposition are expensive, we recast sub-question generation as a span prediction problem and show that our method, trained using only 400 labeled examples, generates sub-questions that are as effective as human-authored sub-questions. We also introduce a new global rescoring approach that considers each decomposition (i.e. the sub-questions and their answers) to select the best final answer, greatly improving overall performance. Our experiments on HotpotQA show that this approach achieves the state-of-the-art results, while providing explainable evidence for its decision making in the form of sub-questions.
Forward citations
Cited by 3 Pith papers
-
Retrieving a Set, Not Independent Passages: Set-Level Compatibility Learning for Efficient Set Exploration
Set-level margin training that ranks complete gold-compatible passage sets above incomplete or noisy ones, implemented with ParaSet exploration and SetCE reranking, improves multi-hop retrieval and QA and complements ...
-
SearchOS-V1: Towards Robust Open-Domain Information-Seeking Agent Collaboration
A multi-agent web-search framework that stores progress in shared evidence, coverage, and failure state reports the best F1 scores among compared baselines on WideSearch (80.3 item F1) and GISA (76.5 set F1).
-
DeepResearch-9K: A Challenging Benchmark Dataset of Deep-Research Agent
A synthetic benchmark of 9,000 multi-hop web-research questions with difficulty tiers and teacher-generated search trajectories, plus an open-source RL training framework that reportedly lets 3B-parameter agents beat ...
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.