Understanding Attribution Explanations

Attribution explanations highlight specific parts of a table—such as rows, columns, or cells—that are most relevant to the answer provided by a TableQA system. These explanations help you understand which data points the system considered important when generating the answer.

Example: 1947 Kentucky Wildcats Football Team

Statement to verify: "The Wildcats kept the opposing team scoreless in four games."

Game	Date	Opponent	Result	Wildcats Points	Opponents	Record
1	9999-09-20	Ole Miss	Loss	7	14	0 - 1
2	9999-09-27	Cincinnati	Win	20	0	1 - 1
4	9999-10-11	9 Georgia	Win	26	0	3 - 1 , 20
5	9999-10-18	10 Vanderbilt	Win	14	0	4 - 1 , 14
9	9999-11-15	Evansville	Win	36	0	7 - 2

In this example, the TableQA system has highlighted specific rows and cells to explain its reasoning:

The entire rows for games 2, 4, 5, and 9 are highlighted in yellow.
Within these rows, the "Opponents" column cells containing "0" are highlighted in green.

These highlights indicate that the system identified four games where the opposing team did not score, verifying the statement as true. The yellow highlighting shows the relevant rows, while the green highlighting represents the cells containing fine-grained information needed to verify the statement.

By using different colors for highlighting, the system provides a more nuanced explanation:

Yellow highlights (rows): Show the overall context of the relevant games.
Green highlights (cells): Pinpoint the exact data points (opposing team's score of 0) that directly answer the question.

This multi-level highlighting helps users quickly grasp both the broad context and the specific details that support the system's answer.

During the experiment, you will compare different methods that provide these types of explanations. Your task will be to evaluate which explanations are most clear and helpful in understanding the system's reasoning.