- Rating
- 1
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 1
- Soundness
- 2
Read review
Paper summary
This paper proposes SentiHarness, a recursive framework that jointly optimizes multimodal evidence acquisition, cross-modal integration, and reasoning strategies for sentiment recognition. It further investigates model–Harness interactions and introduces Harness-aware SFT. Experiments on CH-SIMS, CMU-MOSI, and MELD demonstrate performance improvements over the base model and several existing methods.
Critical strengths
-
The paper extends recursive Harness optimization to multimodal sentiment recognition, jointly searching evidence acquisition and reasoning strategies rather than optimizing prompts alone.
-
The experiments show consistent improvements over fixed-exposure reasoning search across three CH-SIMS search trajectories. The model–Harness interaction analysis also provides useful insights into model adaptation.
Critical weaknesses
-
The search jointly changes modality exposure, call structure, evidence organization, and decision rules. Without isolating these components, the source of the performance improvements remains unclear.
-
Although recent methods such as GEPA and Meta-Harness are discussed, direct experimental comparisons are missing, making it difficult to assess the benefits of the proposed search framework over existing optimization approaches.
-
The main controlled adaptation result relies on a single training run. The marginal Harness-utility recovery is not statistically significant, while CMU-MOSI and MELD use unmatched training budgets, weakening the generality of the adaptation claim.
-
The experiments primarily use one backbone model. Moreover, Appendix L shows that directly transferring the CH-SIMS Harness to CMU-MOSI substantially reduces accuracy, raising concerns about dataset-specific optimization.
Questions for authors
-
Can the authors provide component-level ablations and compute-matched comparisons to identify which search operations contribute most to the improvements?
-
How does SentiHarness compare with recent automatic program or Harness optimization methods under the same backbone and search budget?
-
Does the proposed framework remain effective with different backbone models, and how can the substantial performance degradation in cross-dataset Harness transfer be explained?