Wen-Tau Yih, Victoria Xi, Lin, Hu Xu, James Glass, Yung-Sung Chuang, Zhaofeng Wu, Benjamin Cohen-Wang, Shannon Shen, Shang-Wen Li
We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
We introduce SelfCite, a novel self-supervised approach that aligns LLMs to generate high-quality, fine-grained, sentence-level citations for the statements in their generated responses. Instead of only relying on costly and labor-intensive annotations, SelfCite leverages a reward signal provided by the LLM itself through context ablation: If a citation is necessary, removing the cited text from the context should prevent the same response; if sufficient, retaining the cited text alone should preserve the same response. This reward can guide the inference-time best-of-N sampling strategy to improve citation quality significantly, as well as be used in preference optimization to directly fine-tune the models for generating better citations. The effectiveness of SelfCite is demonstrated by increasing citation F1 up to 5.3 points on the LongBench-Cite benchmark across five long-form question answering tasks. The source code is available at https://github.com/ facebookresearch/SelfCite.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2502.09604")
get_code_for_paper("2502.09604")
have("2502.09604")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2502.09604.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2502.09604)
Connect an agent — have() is free.