Human-CentricAI
/

LLM-Refusal-Classifier

Model card Files Files and versions

Human-CentricAI commited on 11 days ago

Commit

0d9379e

·

verified ·

1 Parent(s): 638d389

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -14,7 +14,7 @@ The model assigns one of five possible labels:
 3 (**Refusal Capability**): The model refuses to answer due to its own limitations, lack of information, or lack of ability to provide an adequate response. <br />
 4 (**Disclaimer Capability**): The model signals its limitations but attempts to provide an answer within its capacity  <br />
-Please cite: <br /> LLM Content Moderation and User Satisfaction: Evidence from Response Refusals in Chatbot Arena (under review).
 References <br />
 [1] Liu, Y.; Ott, M.; Goyal, N.; Du, J.; Joshi, M.; Chen, D.; ... & Stoyanov, V. (2019). Roberta: A robustly optimized bert pretraining approach. arXiv preprint arXiv:1907.11692. <br />

 3 (**Refusal Capability**): The model refuses to answer due to its own limitations, lack of information, or lack of ability to provide an adequate response. <br />
 4 (**Disclaimer Capability**): The model signals its limitations but attempts to provide an answer within its capacity  <br />
+Please cite: <br /> Pasch, S. (2026). LLM content moderation and user satisfaction: evidence from response refusals in Chatbot Arena. Behaviour & Information Technology, 45(10), 2007–2031. https://doi.org/10.1080/0144929X.2025.2565668.
 References <br />
 [1] Liu, Y.; Ott, M.; Goyal, N.; Du, J.; Joshi, M.; Chen, D.; ... & Stoyanov, V. (2019). Roberta: A robustly optimized bert pretraining approach. arXiv preprint arXiv:1907.11692. <br />