Measuring Attribution in Natural Language Generation Models
This work addresses the need for reliable attribution assessment in NLG models, which is crucial for applications like conversational QA and summarization, though it appears incremental as it builds on existing evaluation practices.
The authors tackled the problem of evaluating whether natural language generation models produce verifiable information by introducing the Attributable to Identified Sources (AIS) framework, and they validated it through human evaluation studies across three tasks, suggesting it could serve as a common evaluation method.
With recent improvements in natural language generation (NLG) models for various applications, it has become imperative to have the means to identify and evaluate whether NLG output is only sharing verifiable information about the external world. In this work, we present a new evaluation framework entitled Attributable to Identified Sources (AIS) for assessing the output of natural language generation models, when such output pertains to the external world. We first define AIS and introduce a two-stage annotation pipeline for allowing annotators to appropriately evaluate model output according to AIS guidelines. We empirically validate this approach on generation datasets spanning three tasks (two conversational QA datasets, a summarization dataset, and a table-to-text dataset) via human evaluation studies that suggest that AIS could serve as a common framework for measuring whether model-generated statements are supported by underlying sources. We release guidelines for the human evaluation studies.