Papers with sentiment and toxicity
Perturbation Sensitivity Analysis to Detect Unintended Model Biases (D19-1)
Copied to clipboard
| Challenge: | Recent research shows that data-driven NLP models may inadvertently capture, reflect and sometimes amplify various social biases present in the language data they are trained on. |
| Approach: | They propose a generic evaluation framework that detects unintended model biases related to named entities and requires no new annotations or corpora. |
| Outcome: | The proposed framework detects unintended model biases related to named entities and requires no new annotations or corpora. |
Probing Social Identity Bias in Chinese LLMs with Gendered Pronouns and Social Groups (2026.findings-acl)
Copied to clipboard
| Challenge: | Large language models (LLMs) are increasingly deployed in user-facing applications, raising concerns that they reflect and amplify social biases. |
| Approach: | They propose a Mandarin-specific evaluation framework to examine social identity biases in Chinese LLMs using Mandarin-based prompts. |
| Outcome: | The proposed framework compares ingroup (“We”) and outgroup (“They”) framings across 240 social groups salient in the Chinese context, using a two-tiered measurement framework that assesses both sentiment and toxicity. |