MétaCan
Menu
Back to cohort
Record W4414360383 · doi:10.24963/ijcai.2025/1141

Reflective Verbal Reward Design for Pluralistic Alignment

2025· article· en· W4414360383 on OpenAlexaff
Carter Blair, Kate Larson, Edith Law

Bibliographic record

Venuenot available
Typearticle
Languageen
FieldComputer Science
TopicEducational Research and Pedagogy
Canadian institutionsUniversity of Waterloo
Fundersnot available
KeywordsReinforcement learningConstruct (python library)Context (archaeology)Function (biology)Corrective feedbackLanguage modelReward system

Abstract

fetched live from OpenAlex

AI agents are commonly aligned with "human values" through reinforcement learning from human feedback (RLHF), where a single reward model is learned from aggregated human feedback and used to align an agent's behavior. However, human values are not homogeneous--different people hold distinct and sometimes conflicting values. Aggregating feedback into a single reward model risks disproportionately suppressing minority preferences. To address this, we present a novel reward modeling approach for learning individualized reward models. Our approach uses a language model to guide users through reflective dialogues where they critique agent behavior and construct their preferences. This personalized dialogue history, containing the user's reflections and critiqued examples, is then used as context for another language model that serves as an individualized reward function (what we call a "verbal reward model") for evaluating new trajectories. In studies with 30 participants, our method achieved a 9-12% improvement in accuracy over non-reflective verbal reward models while being more sample efficient than traditional supervised learning methods.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

How this classification was reachedexpand

Full frame machine prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.

metaresearch head score (Codex)0.006
metaresearch head score (Gemma)0.022
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Not applicable · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: none
Teacher disagreement score0.006
Threshold uncertainty score0.031

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0060.022
Meta-epidemiology (narrow)0.0010.001
Meta-epidemiology (broad)0.0010.001
Bibliometrics0.0010.001
Science and technology studies0.0010.002
Scholarly communication0.0020.005
Open science0.0030.004
Research integrity0.0010.002
Insufficient payload (model declined to judge)0.0060.002

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.096
GPT teacher head0.422
Teacher spread0.326 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designNot applicable
Domainnot available
GenreEmpirical

How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".

Quick stats

Citations0
Published2025
Admission routes1
Has abstractyes

Explore more

Same topicEducational Research and PedagogyFrench-language works237,207