Labels have Human Values: Value Calibration of Subjective Tasks
Building NLP systems for subjective tasks requires one to ensure their alignment to contrasting human values. We propose the MultiCalibrated Subjective Task Learner framework (MC-STL), which clusters annotations into identifiable human value clusters by three approaches (similarity of annotator rationales, expert-value taxonomies or rater's sociocultural descriptors) and calibrates predictions for each value cluster by learning cluster-specific embeddings. We demonstrate MC-STL on several subjective learning settings, including ordinal, binary, and preference learning predictions, and evaluate it on multiple datasets covering toxic chatbot conversations, offensive social media posts, and human preference alignment. The results show that MC-STL consistently outperforms the baselines that ignore the latent value structure of the annotations, delivering gains in discrimination, value-specific calibration, and disagreement-aware metrics.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
CLAVE: An Adaptive Framework for Evaluating Values of LLM Generated Responses
The rapid progress in Large Language Models (LLMs) poses potential risks such as generating unethical content. Assessing LLMs' values can help expose their misalignment, but relies on reference-free evaluators, e.g., fin…
Calibration without labels in multiple testing
Large-scale hypothesis testing supports probability claims about individual hypotheses, as in empirical Bayes methods for estimating local false discovery rates. We study how such claims can be interpreted as approximate…
Eigenvalue Calibration for Semantic Embeddings of Large Language Models
Uncertainty quantification is central to the reliable deployment of large language models (LLMs), and eigenvalues of semantic embeddings have recently emerged as a key tool in state-of-the-art methods. However, conventio…
Validation of ML-UQ calibration statistics using simulated reference values: a sensitivity analysis
Some popular Machine Learning Uncertainty Quantification (ML-UQ) calibration statistics do not have predefined reference values and are mostly used in comparative studies. In consequence, calibration is almost never vali…
DiagnosticSensitivityUncertainty QuantificationDon't Forget Your Reward Values: Language Model Alignment via Value-based Calibration
While Reinforcement Learning from Human Feedback (RLHF) significantly enhances the generation quality of Large Language Models (LLMs), recent studies have raised concerns regarding the complexity and instability associat…
Language ModelingLanguage Modelling