CEval: A Benchmark for Evaluating Counterfactual Text Generation
This addresses a methodological gap for researchers in NLP by providing a standardized evaluation framework, though it is incremental as it builds on existing datasets and methods.
The authors tackled the problem of inconsistent evaluation in counterfactual text generation by proposing CEval, a benchmark that unifies metrics, datasets, and baselines, and found that no method perfectly balances counterfactual effectiveness and text quality.
Counterfactual text generation aims to minimally change a text, such that it is classified differently. Judging advancements in method development for counterfactual text generation is hindered by a non-uniform usage of data sets and metrics in related work. We propose CEval, a benchmark for comparing counterfactual text generation methods. CEval unifies counterfactual and text quality metrics, includes common counterfactual datasets with human annotations, standard baselines (MICE, GDBA, CREST) and the open-source language model LLAMA-2. Our experiments found no perfect method for generating counterfactual text. Methods that excel at counterfactual metrics often produce lower-quality text while LLMs with simple prompts generate high-quality text but struggle with counterfactual criteria. By making CEval available as an open-source Python library, we encourage the community to contribute more methods and maintain consistent evaluation in future work.