# PACIFIC: Towards Proactive Conversational Question Answering over Tabular and Textual Data in Finance

Source: [PACIFIC: Towards Proactive Conversational Question Answering over Tabular and Textual Data in Finance](<https://www.sota2.com/research/paper/68fa6ecf1e209131cea424f9>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T01:07:49.028Z

Authors: Yang Deng, Wenqiang Lei, Wenxuan Zhang, Wai Lam, Tat-Seng Chua

Published: 2022-10-17T08:06:56.000Z

## Abstract

To facilitate conversational question answering (CQA) over hybrid contexts in finance, we present a new dataset, named PACIFIC. Compared with existing CQA datasets, PACIFIC exhibits three key features: (i) proactivity, (ii) numerical reasoning, and (iii) hybrid context of tables and text. A new task is defined accordingly to study Proactive Conversational Question Answering (PCQA), which combines clarification question generation and CQA. In addition, we propose a novel method, namely UniPCQA, to adapt a hybrid format of input and output content in PCQA into the Seq2Seq problem, including the reformulation of the numerical reasoning process as code generation. UniPCQA performs multi-task learning over all sub-tasks in PCQA and incorporates a simple ensemble strategy to alleviate the error propagation issue in the multi-task learning by cross-validating top-$k$ sampled Seq2Seq outputs. We benchmark the PACIFIC dataset with extensive baselines and provide comprehensive evaluations on each sub-task of PCQA.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2210.08817>)

[PDF](<https://arxiv.org/pdf/2210.08817.pdf>)