LetTokenBurn
Sign in
Auto71%Harbor: pendingMathKnowledge & Reasoning

ConvFinQA

Conversational Finance Question Answering

ConvFinQA is a dataset designed to study the chain of numerical reasoning in conversational question answering.

PaperRepoLeaderboardHomepage

How to run

ltb · convfinqa
$ npm i -g lettokenburn-cli
$ ltb bench info convfinqa

External harness. No Harbor adapter has been generated for this benchmark yet. `ltb bench info` prints the known links.

Runs happen on your machine with your own subscription; only the score summary is pushed. CLI docs

Scores

1 sourced entry
HarnessSourceConfidenceLink
GPT-476.5N/AIndependentmediumMay 10, 2023arxiv.org

Every number links to where it was published. Low-confidence rows are muted and need per-cell verification.

Reproduced by the community

All runs
Loading community runs…

About

ConvFinQA is a dataset designed to study the chain of numerical reasoning in conversational question answering. The dataset contains 3892 conversations containing 14115 questions where 2715 of the conversations are simple conversations, and the rest 1,177 are hybrid conversations.

Source: ConvFinQA: Exploring the Chain of Numerical Reasoning in Conversational Finance Question Answering

Image Source: https://arxiv.org/pdf/2210.03849.pdf