Pith. sign in

REVIEW 4 cited by

What are you optimizing for? Aligning Recommender Systems with Human Values

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2107.10939 v1 pith:BNLINCHM submitted 2021-07-22 cs.IR cs.CYcs.LG

What are you optimizing for? Aligning Recommender Systems with Human Values

classification cs.IR cs.CYcs.LG
keywords valuesalignmenthumanidentifypracticerecommenderstakeholderssystems
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

We describe cases where real recommender systems were modified in the service of various human values such as diversity, fairness, well-being, time well spent, and factual accuracy. From this we identify the current practice of values engineering: the creation of classifiers from human-created data with value-based labels. This has worked in practice for a variety of issues, but problems are addressed one at a time, and users and other stakeholders have seldom been involved. Instead, we look to AI alignment work for approaches that could learn complex values directly from stakeholders, and identify four major directions: useful measures of alignment, participatory design and operation, interactive value learning, and informed deliberative judgments.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 4 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Normative Alignment of Recommender Systems via Internal Label Shift

    cs.IR 2026-07 accept novelty 6.0

    NAILS applies internal label shift inside a hierarchical item-attribute model to force a target marginal attribute distribution on recommendations without retraining.

  2. Unsolved Problems in ML Safety

    cs.LG 2021-09 accept novelty 6.0

    The paper presents a roadmap that identifies four unsolved problems in ML safety: robustness against hazards, monitoring for hazards, alignment of model goals with human intent, and systemic safety.

  3. Transparent and Controllable Recommendation Filtering via Multimodal Multi-Agent Collaboration

    cs.IR 2026-04 unverdicted novelty 4.0

    A multi-agent multimodal system with fact-grounded adjudication and a dynamic two-tier preference graph cuts false positives in content filtering by 74.3% and nearly doubles F1-score versus text-only baselines while s...

  4. An Overview of Catastrophic AI Risks

    cs.CY 2023-06 accept novelty 3.0

    The paper categorizes sources of catastrophic AI risks into malicious use, AI race, organizational risks, and rogue AIs, providing illustrative stories and mitigation suggestions for each.