Yixiao Song

Yixiao Song has 3 papers in our library, in 2023–2024, most of them on Question answering, Text generation, Evaluation & benchmarks; often with Mohit Iyyer, Eunsol Choi, Fangyuan Xu.

3 papers in our library · 2023–2024

The profile is the library's match of the name; two people with one name are not always told apart.

Concepts, shelves and topics

Of its works in our library: the number of works on each and its rating among them.

The most cited first (OpenAlex and our library).

Paraphrasing evades detectors of AI-generated text, but retrieval is an effective defense (2023 · 304 citations)
Tools that flag machine-written text include watermarks, statistical detectors such as DetectGPT and GPTZero, and trained classifiers like OpenAI's. They are increasingly used against fake content and plagiarism, but nobody had tested them systematically against rewriting.
A Critical Evaluation of Evaluations for Long-form Question Answering (2023 · 112 citations)
Evaluating long-form question answering (LFQA) is hard because answers are open-ended. Earlier work mostly relied on crowdworkers' A/B preferences and string-overlap metrics such as ROUGE. Xu et al. study both human and automatic evaluation of long answers. They recruited domain experts in seven fields through…
VeriScore: Evaluating the factuality of verifiable claims in long-form text generation (2024 · 69 citations)
Metrics for long-form factuality such as FactScore and SAFE split a text into atomic claims and check every one. They assume all content can be checked. In tasks like long-form QA (LFQA), responses mix facts with analogies, advice, opinions and hypotheticals, so these metrics unfairly penalise models.

6 co-authors with a page, the most papers together first.

Where their works here were published, the most works first, with the editions of those that have a page.

Papers of our library cite their works 307 times (of the 141,840 papers whose bibliographies we read); 22 citing papers with a page here →.

Updated 24 October 2026