Ablation Studies in Sentiment Analysis: Impact of LLM Roles and Consensus

cover
20 May 2024

Authors:

(1) Xiaofei Sun, Zhejiang University;

(2) Xiaoya Li, Shannon.AI and Bytedance;

(3) Shengyu Zhang, Zhejiang University;

(4) Shuhe Wang, Peking University;

(5) Fei Wu, Zhejiang University;

(6) Jiwei Li, Zhejiang University;

(7) Tianwei Zhang, Nanyang Technological University;

(8) Guoyin Wang, Shannon.AI and Bytedance.

Abstract and Intro

Related Work

LLM Negotiation for Sentiment Analysis

Experiments

Ablation Studies

Conclusion and References

5 Ablation Studies

In this section, we perform ablation studies on the Twitter dataset to better understand the mechanism behind the negotiation framework.

Table 2: Performance on the Twitter dataset with GPT-3.5 and GPT-4 taking different roles. G denotes generator and D denotes discriminator.

Table 3: Consensus percentage for different setups on the Twitter dataset. G3.5-D4 denotes GPT-3.5 acts as the generator and GPT-4 acts as the discriminator.

5.1 Who takes which role matters

In the negotiation framework, there are two roles, the generator and the discriminator, which two separate LLMs take. Table 2 shows the performance for setups where GPT-3.5 and GPT-4 take different roles.

As can be seen, when GPT-3.5 acts as the generator, and GPT-4 acts as the discriminator (G3.5-D4 for short), the performance (68.8) is better than single GPT-3.5 without negotiation (65.2), but worse than single GPT-4 without negotiation (69.5). In contrast, negotiation-based configurations with GPT-4 acting as the generator (G4-D3.5 and G4-D4) consistently outperforms standalone GPT-4 or GPT-3.5 models without negotiation. These results underscore the pivotal role that the generator plays in influencing the negotiation outcome. Furthermore, we observe G4- D3.5 can beat G4-D4. We attribute such advantage to the hypothesis that utilizing heterogeneous LLMs for distinct roles could optimize the negotiation’s performance.

5.2 Consensus Percentage

Table 3 consensus percentage for different setups. As can be seen, when GPT-4 acts as the generator, the negotiation is more likely to reach a consensus, or reach a consensus in fewer turns. The explanation is intuitive: for the twitter task, we can see from table 1 that GPT-4 obtains better performances that GPT-3.5, which means the reasoning process for GPT-4 is more sensible than 3.5, making the decision of the former more likely to be agreed on.

Table 4: Effect of removing the reasoning process on the Twitter dataset.

5.3 Effect of the Reasoning Process

In the negotiation process, LLMs are asked to articulate the reason process, a strategy akin to CoT(Wei et al., 2022b). We examine the importance for listing reasons in negotiation by removing the reasoning process and asking LLMs to only output decisions. Results are shown in Table 4. As can be seen, for the three setups, single GPT-3.5, where only GPT-3.5 is used without negotiation, single GPT-4, where only GPT-4 is used without negotiation, and GPT-3.5+GPT-4 where negotiation is employed, performances all degrade when the reasoning process is removed. But interestingly, we see a greater degrade (-2.3) for the negotiation than the single model setup (-1.2 for single-GPT-3.5 and -0.9 for single-GPT-4). This is in accord with our expectation as the reasoning process is of greater significance in the negotiation setup.

This paper is available on arxiv under CC 4.0 license.