- Rating
- 1
- Confidence
- 3
- Informativeness
- 1
- Presentation
- 2
- Soundness
- 3
Read review
Paper summary
The paper focuses on the synthetic generation of cognitive biases (e.g., confirmation bias) with GPT-4o-2024-08-06, given a predefined generation taxonomy containing 10 cognitive biases, 5 domains, and 31 bias–domain couplings. This taxonomy was taken from a larger, private taxonomy curated by a trained psychologist.
The authors vary how detailed the information given to the generating model is:
- Public uses literature-based definitions of the biases.
- Atlas-DJ contains the psychologist's definitions of the biases along with domain justifications.
- Atlas-Full, the most detailed, additionally contains a reference example and instructs the generating model not to copy or overlap with it during generation.
The same psychologist who designed the original taxonomy evaluates the generated data blind for construct fidelity, using the following metrics:
- bias identification (primary outcome),
- neighboring-bias contamination (primary outcome),
- domain relevance (secondary/descriptive outcome),
- usability (secondary/descriptive outcome),
- editorial decision (secondary/descriptive outcome), and
- a loose or strict composite of the preceding metrics (primary outcome).
At a high level, the authors find that Atlas-Full improves over Public on contamination-free generation (by 8.4 pp), on the strict fidelity composite (by 8.9 pp), and on the soft composite (by 7.4 pp). However, the authors report that these contrasts remain uncertain.
Critical strengths
Sound metrics and statistical analysis. The chosen metrics are intuitive and appropriate. The sampling and statistical analysis are careful and sufficient to back the key claims made. The answers to the RQs are sufficiently corroborated by the findings and analysis.
Critical weaknesses
-
Clarity of the abstract and introduction. The abstract and introduction introduce numerous terms that cannot be interpreted until much later in the paper. For instance, the abstract mentions "neighboring constructs," "generation cells," and "no-copy and overlap safeguards" without clarifying them. Similarly, "zero confidence intervals" and "Holm correction" appear without any discussion of their implications, which makes them hard to interpret. Paragraphs 3 and 4 of the introduction repeat the same information in the abstract but offer no additional context to interpret it clearly. Much of this information remains unclear until later in the paper, leaving the reader hanging. The paper becomes much clearer from the related work section onward. It would be great if the authors carefully revisited this formative text so that it is self-contained and interpretable at a high level, giving a good foundation for interpreting the rest of the paper. It would help to introduce terms and jargon only when there is enough context to interpret them.
-
Scope, novelty, and impact.
-
The premise of the work focuses specifically on construct fidelity in the context of cognitive bias generation. This is a rather narrow focus, especially since the authors do not discuss how it may generalize to the construct fidelity of synthetic data more broadly.
-
The authors study the generation properties of a single model, GPT-4o, so it is unclear whether their findings on construct fidelity apply beyond this model.
-
The takeaways are the principles embodied in Atlas-Full. If we were to synthesize what their value to the community could be:
◦ (a) examples help improve construct fidelity (it is well known in the field that in-context examples improve synthesis quality); ◦ (b) clear definitions help with generation quality (which is intuitive); and ◦ (c) expert definitions of cognitive biases improve over public/literature definitions (which applies only narrowly, to types of data whose public and expert definitions differ).
Altogether, although the empirical investigation is sound and apt, the narrow focus of the premise, the single-model setting, and the applicability and impact of the findings for the community account for my recommended decision. Finally, the authors' stated impact of this work is to motivate synthesizing cognitive data in an iterative data-development loop. This appears intuitive and is already widely adopted in domains beyond cognitive biases.
Questions for authors
- Why is cognitive bias data an appropriate setting for studying the construct fidelity of synthetic data?
- Concretely, who in the ICLR/academic community does this work benefit, and how?
- Are there generalizable construct-fidelity takeaways for the ML community invested in generating synthetic data? If so, how do they differ from existing data synthesis practices?