Read the paper PDF
Open the PDF in a new tab If the panel above stays blank, the publisher does not allow embedding. The link always works.
Jessica Quaye, Alicia Parrish, Charvi Rastogi, Minsuk Kahng, Oana Inel, Lora Aroyo, Vijay Janapa Reddi — Proceedings of the 2026 ACM Conference on Fairness, Accountability, and Transparency (FAccT 2026), DOI: 10.1145/3805689.3812210. Venue and full author list confirmed via the FAccT 2026 proceedings listing and a co-author’s (Minsuk Kahng’s) publications page. My earlier note flagged the venue as unconfirmed (“ACM Conference, 2026 — likely FAccT or CHI”); it is now confirmed as FAccT 2026, not CHI.
Survey table
| Column | Entry |
|---|---|
| Specific authors | Jessica Quaye, Alicia Parrish, Charvi Rastogi, Minsuk Kahng, Oana Inel, Lora Aroyo, Vijay Janapa Reddi |
| Objectives | Surface latent, context-dependent risks in text-to-image models that neither pure human nor pure automated red-teaming catches alone, via a hybrid human-in-the-loop methodology |
| Methodology | Automation scales red-teaming coverage (prompt volume, variation, iteration speed) while humans keep the judgment calls about what counts as a latent risk; sits between purely manual efforts (Adversarial Nibbler) and purely automated distribution modeling (DREAM); the specific automation technique is unconfirmed pending the proceedings PDF |
| Dataset | T2I models under test and sample sizes unconfirmed from my pass (bibliographic facts verified, methodological depth not) |
| Open source | Unknown; no artifact information retrievable from the proceedings listing |
| Advantages | Directly rebuts “human vs automated” framing with a division of labor matched to what each is good at; latent-harm focus targets exactly the failures automated classifiers miss; FAccT venue grounds the harm taxonomy in fairness scholarship rather than pure ASR counting |
| Disadvantages | Methodological specifics (models, operationalization of latent risk, quantitative results) unverified without full text; T2I modality, so only the hybrid methodology transfers to my text-LLM niche; human-in-the-loop designs carry an intrinsic cost/scale ceiling the paper itself acknowledges |
Core Contribution
The paper’s framing rebuts “just pick one” debates about red-teaming strategy: pure human red-teaming has judgment and nuance but doesn’t scale to the volume needed to characterize a deployed system’s risk surface; pure automated red-teaming scales but misses the latent, context-dependent harms that require human interpretation to even recognize as harms. The contribution is a hybrid, human-in-the-loop methodology that uses automated techniques to augment human red-teamers — extending their reach rather than replacing their judgment — applied to text-to-image (T2I) generative systems.
Method
Based on the confirmed title and framing, the approach sits in the “human-in-the-loop” category of red-teaming methods, distinct from purely manual approaches (e.g., Adversarial Nibbler) or purely automated distribution-modeling approaches (e.g., DREAM). The design logic — evident from the title itself — is to use automation to scale red-teaming coverage (more prompts, more variation, faster iteration) while keeping humans in the loop for the judgment calls about what counts as a “latent risk,” which is exactly what automated classifiers tend to miss. I was not able to retrieve the full published methods section (the FAccT proceedings listing and co-author publication page gave only citation and DOI, not full text), so I’m flagging as unconfirmed the specific automation technique used, the T2I models evaluated, and any quantitative results — these require a direct read of the proceedings PDF.
Limitations
- I could not verify methodological specifics (which T2I models, how “latent risk” is operationalized as a measurable outcome, sample sizes). This entry is confirmed on bibliographic facts (real paper, real venue, real authors, real DOI) but not yet confirmed on methodological depth.
- Domain mismatch with my core text-only LLM focus: this is T2I, not language-model red-teaming. What transfers is the hybrid methodology, not the specific failure modes found in image generation.
- Human-in-the-loop methods carry a structural cost/scale tradeoff by design — the paper’s own premise is that this is a deliberate compromise, not a free lunch. It likely doesn’t scale as far as fully automated red-teaming even where it catches more.
Relevance to My Niche
Moderate, methodological relevance rather than direct subject-matter relevance. My niche is red-teaming LLMs across languages and quantization levels — a different modality than T2I — but the underlying design question is shared: who or what is best positioned to recognize a given failure mode, and does that change with scale? For multilingual red-teaming specifically, an analogous hybrid design looks necessary: automated translation/back-translation can scale coverage across many languages, but recognizing whether a translated jailbreak actually landed as intended (versus mistranslating into something harmless, or something differently harmful) plausibly needs a human fluent in that language in the loop — exactly the human/automation division of labor this paper is structured around. I’d treat this as a landscape/methodology reference rather than a direct empirical anchor for the niche.