Perspective Transition of Large Language Models for Solving Subjective Tasks
This addresses the problem of improving LLM responses for subjective tasks, which is important for users needing nuanced and contextually appropriate outputs, though it is incremental as it builds on existing in-context learning techniques.
The paper tackles the limited performance of large language models (LLMs) on subjective tasks by proposing Reasoning through Perspective Transition (RPT), a method that dynamically selects among direct, role, and third-person perspectives, and it outperforms fixed-perspective methods like chain-of-thought prompting across 12 subjective tasks using models such as GPT-4 and Llama-3.
Large language models (LLMs) have revolutionized the field of natural language processing, enabling remarkable progress in various tasks. Different from objective tasks such as commonsense reasoning and arithmetic question-answering, the performance of LLMs on subjective tasks is still limited, where the perspective on the specific problem plays crucial roles for better interpreting the context and giving proper response. For example, in certain scenarios, LLMs may perform better when answering from an expert role perspective, potentially eliciting their relevant domain knowledge. In contrast, in some scenarios, LLMs may provide more accurate responses when answering from a third-person standpoint, enabling a more comprehensive understanding of the problem and potentially mitigating inherent biases. In this paper, we propose Reasoning through Perspective Transition (RPT), a method based on in-context learning that enables LLMs to dynamically select among direct, role, and third-person perspectives for the best way to solve corresponding subjective problem. Through extensive experiments on totally 12 subjective tasks by using both closed-source and open-source LLMs including GPT-4, GPT-3.5, Llama-3, and Qwen-2, our method outperforms widely used single fixed perspective based methods such as chain-of-thought prompting and expert prompting, highlights the intricate ways that LLMs can adapt their perspectives to provide nuanced and contextually appropriate responses for different problems.