Papers with human supervision
Using Crowd Agreement for Wordnet Localization (L18-1)
Copied to clipboard
| Challenge: | Lexical-semantic resources like WordNet are a fundamental resource for many NLP and semantic applications. |
| Approach: | They propose a crowdsourcing workflow that consists of synset localization and validation . they use inter-rater agreement metrics to estimate the precision of the results . |
| Outcome: | The proposed method is cost-effective and provides a good trade-off between quality and speed of progress. |
Query-Efficient Black-Box Red Teaming via Bayesian Optimization (2023.acl-long)
Copied to clipboard
| Challenge: | Existing methods for generating test cases and querying fail to be query-efficient . generative models can be used for open-domain dialogue, prompt continuation, text-to-image generation . |
| Approach: | They propose a query-efficient method that iteratively finds diverse positive test cases leading to model failures by utilizing user input and past evaluations. |
| Outcome: | The proposed method finds a significantly larger number of diverse positive test cases under limited query budget than baseline methods. |
Generative Reward Modeling via Synthetic Criteria Preference Learning (2025.acl-long)
Copied to clipboard
| Challenge: | Generative Reward Models (GenRMs) leverage synthesized Chains of Thought (CoT) but this approach introduces risks of overoptimization due to the inability to guarantee the correctness of the CoTs. |
| Approach: | They propose a criteria-based preference tree for GenRMs that uses chain of thought to generate reasoning . they show that synthesized data can be learned using a long CoT format . |
| Outcome: | The proposed model shows significant improvements over baselines on multiple human preference benchmarks. |