- Rating
- 2
- Confidence
- 2
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
The manuscript addresses the difficulty of LLMs in distinguishing implicit emotional expressions from explicit emotion-related questions and proposes a neuro-symbolic reasoning framework named PAIR. The framework decomposes emotion understanding into five semantic regions: explicit emotion, implicit emotion, affective stance, pragmatic intent, and fine-grained emotion, and establishes their compositional relationships through predefined symbolic structures. By combining SFT and RL, PAIR enhances the model's ability to recognize these distinctions. Experimental results demonstrate the effectiveness of the proposed method on Qwen3-4B and Qwen3-1.7B.
Critical strengths
-
The research problem addressed in the manuscript is important and well motivated.
-
The proposed PAIR method is well designed and offers good interpretability.
-
The experimental results provide strong evidence for the effectiveness of PAIR.
Critical weaknesses
-
The manuscript appears to overstate the concept of Neuro-Symbolic Reasoning, as the proposed method does not actually learn a symbolic reasoning process.
-
The manuscript does not report the actual training data size, class distribution, or Teacher accuracy before and after filtering. The performance gains of PAIR-SFT may therefore stem from data filtering rather than structured reasoning.
-
The authors should further clarify why it is necessary to model deterministic label relationships as structures that need to be learned.
-
The manuscript lacks essential ablation studies, such as ablations on the Global, Local, and Structural Rewards.
-
The weights used to combine the Global, Local, and Structural Advantages should be explicitly reported in the manuscript.
Questions for authors
Please refer to weaknesses
6 comments
Response to Reviewer X4JK – [2/2]
[W2] How was the PAIR-SFT training data filtered?
Re: To put the performance comparison in context, we report (1)the training set size and class distribution before and after filtering and (2)how many teacher responses passed the filter, then (3)compare PAIR-SFT with Structured SFT trained on unfiltered responses.
(1) Training set size and class distribution.
We started with 8,000 questions and retained 7,721 training examples. Appendix B.5 reports the class counts before and after filtering.
(2) Filtering results.
The filter required answers to match the reference labels, so 100% of the retained answers matched. The final training set accounts for 33.32% of all recorded trajectories (7,721/23,170).
(3) Structured SFT and PAIR-SFT.
Structured SFT uses unfiltered teacher responses. PAIR-SFT organizes rationales into distinct semantic regions and uses symbolic verification to check the judgments. Table R10 compares the two training setups.
Table R10. Qwen3-4B SFT comparison on CueBench.
| Method | Format | Verification | Affective Stance Acc. | Pragmatic Intent Acc. | Fine-grained Emotion Acc. | Acc Avg. |
|---|---|---|---|---|---|---|
| Structured SFT | ✓ | ✗ | 54.46 | 36.90 | 30.01 | 40.46 |
| PAIR-SFT (Ours) | ✓ | ✓ | 58.53 | 52.97 | 35.37 | 48.96 |
[W4 & W5] How do the three advantage components contribute, and how are they weighted?
Re: Thank you for pointing this out. We (1)compare different combinations of the global, local, and structural advantages to assess each component’s contribution and (2)give the weights used to combine them in the full model.
(1) Ablation results. We ran ablations for the Global, Local, and Structural components and report the results in Table R11.
(2) Advantage weights. In Eq. (16), the weights for the Global, Local, and Structural Advantages are 1, 0.1, and 0.05, respectively.
We will include the ablation results and advantage weights in the revised manuscript.
Table R11. Ablation of the three advantage components.
| Method | Global | Local | Structural | Affective Stance Acc. | Pragmatic Intent Acc. | Fine-grained Emotion Acc. | Acc Avg. |
|---|---|---|---|---|---|---|---|
| Global Only (GRPO) | ✓ | ✗ | ✗ | 65.03 | 60.97 | 45.87 | 57.29 |
| Local Only | ✗ | ✓ | ✗ | 64.20 | 60.40 | 46.40 | 57.00 |
| Structural Only | ✗ | ✗ | ✓ | 60.57 | 50.66 | 33.21 | 48.15 |
| Global + Local | ✓ | ✓ | ✗ | 67.08 | 65.60 | 52.00 | 61.56 |
| Global + Structural | ✓ | ✗ | ✓ | 65.77 | 59.62 | 46.33 | 57.24 |
| Local + Structural | ✗ | ✓ | ✓ | 66.14 | 60.80 | 49.00 | 58.65 |
| PAIR | ✓ | ✓ | ✓ | 70.71 | 67.05 | 54.99 | 64.25 |
The additional experiments and tables took some time to complete, and we appreciate your patience. We will incorporate your suggestions into the revised manuscript. Thank you again for your valuable feedback! If you have any further questions, we would be happy to answer them.
Dear Reviewer,
We hope our response has addressed the concerns raised in the review. As the discussion period is approaching its end, we wanted to check whether there are any remaining questions or points we could further clarify. We would be glad to provide additional detail if helpful.
Best regards, The Authors
Response to Reviewer X4JK – [1/2]
Thank you for your valuable feedback and for recognizing the strengths of our work! We address the weaknesses and questions you raised below.
Re: PAIR (1)links polarity and stance with a fixed rule and (2)uses that rule to check consistency and guide training, while (3)retaining the model’s independent stance judgment as the final prediction.
PAIR's neuro-symbolic formulation uses explicit structural relations to guide training.
(1) Positioning of Neuro-Symbolic Reasoning.
PAIR combines neural semantic reasoning with explicit symbolic constraints. The predefined symbolic rules remain fixed during training.
The model independently predicts Explicit Polarity, Implicit Polarity, and Affective Stance from natural language. These judgments rely on context and different semantic cues.
The predefined composition mapping Ω specifies how these judgments relate. The Structural advantage provides a training signal based on whether the predictions follow this mapping.
The explicit symbolic structure links the model's predictions and guides it as it learns to reason across semantic dimensions.
Reviewer ZESd also noted that this symbolic structure helps localize errors in multi-dimensional affective reasoning and makes compositional consistency an explicit training signal.
(2) Modeling deterministic label relationships.
We keep the deterministic composition rule fixed and use it as an explicit structural prior during training.
The model still has to infer coordinated semantic judgments from natural language, even when the label relationships are deterministic.
Final classification rewards alone provide limited information about conflicts among explicit polarity, implicit polarity, and overall stance. We use Ω to check consistency across these regions and feed the result back into training.
We compared two Qwen3-4B SFT variants with and without explicit modeling of the deterministic relationship between polarity and stance (Table R8).
Table R8. Direct stance prediction on CueBench.
(3) Independent stance prediction.
We use the model's direct stance prediction as the final output. This encourages the model to make its own judgment about the overall affective stance.
Table R9 shows that each method correctly predicts some cases that the other gets wrong.
Table R9. Paired stance prediction outcomes on CueBench.
We use the fixed composition rule to guide the model as it learns to make coordinated affective judgments across semantic dimensions.