RLHF should decompose annotations into dimensions each matched to one of three models—extension, evidence, or authority—instead of applying a single unified pipeline.
Inverse Constitutional
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
abstract
Feedback data is widely used for fine-tuning and evaluating state-of-the-art AI models. Pairwise text preferences, where human or AI annotators select the "better" of two options, are particularly common. Such preferences are used to train (reward) models or to rank models with aggregate statistics. For many applications it is desirable to understand annotator preferences in addition to modelling them - not least because extensive prior work has shown various unintended biases in preference datasets. Yet, preference datasets remain challenging to interpret. Neither black-box reward models nor statistics can answer why one text is preferred over another. Manual interpretation of the numerous (long) response pairs is usually equally infeasible. In this paper, we introduce the Inverse Constitutional AI (ICAI) problem, formulating the interpretation of pairwise text preference data as a compression task. In constitutional AI, a set of principles (a constitution) is used to provide feedback and fine-tune AI models. ICAI inverts this process: given a feedback dataset, we aim to extract a constitution that best enables a large language model (LLM) to reconstruct the original annotations. We propose a corresponding ICAI algorithm and validate its generated constitutions quantitatively based on annotation reconstruction accuracy on several datasets: (a) synthetic feedback data with known principles; (b) AlpacaEval cross-annotated human feedback data; (c) crowdsourced Chatbot Arena data; and (d) PRISM data from diverse demographic groups. As a short and interpretable representation of the original dataset, generated constitutions have many potential use cases: help identify undesirable annotator biases, understand model performance better, scale feedback to unseen data, or adapt models to individual user or group preferences. We release the source code at https://github.com/rdnfn/icai.
years
2026 5representative citing papers
LLawCo extracts misaligned behavioral patterns from agent failures to derive laws, incorporates them via SFT into LLM reasoning, and reports 4.5% and 6.8% success rate gains on PARTNR-Dialog and TDW-MAT benchmarks.
Proposes compiling preference pairs into readable natural-language specifications for inference-time LLM alignment, claiming outperformance over DPO on dense-preference domains.
Alignment plausibility—evidence that an AI system's values, training, and oversight cohere with safe positive health outcomes—should be the regulatory analogue of biological plausibility for LLMs in healthcare.
Positive Alignment is defined as AI systems that support human flourishing pluralistically while staying safe and cooperative, presented as a necessary complement to existing safety-focused alignment research.
citing papers explorer
-
Three Models of RLHF Annotation: Extension, Evidence, and Authority
RLHF should decompose annotations into dimensions each matched to one of three models—extension, evidence, or authority—instead of applying a single unified pipeline.
-
LLawCo: Learning Laws of Cooperation for Modeling Embodied Multi-Agent Behavior
LLawCo extracts misaligned behavioral patterns from agent failures to derive laws, incorporates them via SFT into LLM reasoning, and reports 4.5% and 6.8% success rate gains on PARTNR-Dialog and TDW-MAT benchmarks.
-
Towards Spec Learning: Inference-Time Alignment from Preference Pairs
Proposes compiling preference pairs into readable natural-language specifications for inference-time LLM alignment, claiming outperformance over DPO on dense-preference domains.
-
Alignment Plausibility: A New Standard for Assuring AI in Healthcare
Alignment plausibility—evidence that an AI system's values, training, and oversight cohere with safe positive health outcomes—should be the regulatory analogue of biological plausibility for LLMs in healthcare.
-
Positive Alignment: Artificial Intelligence for Human Flourishing
Positive Alignment is defined as AI systems that support human flourishing pluralistically while staying safe and cooperative, presented as a necessary complement to existing safety-focused alignment research.