Evidence suggests that different prompts lead large language models (LLMs) to
generate responses with varying quality. Yet, little is known about prompts'
effects on response quality in healthcare domains. In this exploratory study,
we address this gap, focusing on a specific healthcare domain: dementia
caregiving. We first developed an innovative prompt template with three
components: (1) system prompts (SPs) featuring 4 different roles; (2) an
initialization prompt; and (3) task prompts (TPs) specifying different levels
of details, totaling 12 prompt combinations. Next, we selected 3 social media
posts containing complicated, real-world questions about dementia caregivers'
challenges in 3 areas: memory loss and confusion, aggression, and driving. We
then entered these posts into GPT-4, with our 12 prompts, to generate 12
responses per post, totaling 36 responses. We compared the word count of the 36
responses to explore potential differences in response length. Two experienced
dementia care clinicians on our team assessed the response quality using a
rating scale with 5 quality indicators: factual, interpretation, application,
synthesis, and comprehensiveness (scoring range: 0-5; higher scores indicate
higher quality).

通过使用 12 个提示组合在 GPT-4 中生成 36 个响应来比较 36 个响应的字数，本研究旨在探索不同提示对医疗保健领域中响应质量的影响，关注特定的医疗保健领域：痴呆症护理。

不同提示对 GPT-4 回答痴呆照料问题质量的影响

Effects of Different Prompts on the Quality of GPT-4 Responses to  Dementia Care Questions

In this paper, we introduce Concise Chain-of-Thought (CCoT) prompting. We
compared standard CoT and CCoT prompts to see how conciseness impacts response
length and correct-answer accuracy. We evaluated this using GPT-3.5 and GPT-4
with a multiple-choice question-and-answer (MCQA) benchmark. CCoT reduced
average response length by 48.70% for both GPT-3.5 and GPT-4 while having a
negligible impact on problem-solving performance. However, on math problems,
GPT-3.5 with CCoT incurs a performance penalty of 27.69%. Overall, CCoT leads
to an average per-token cost reduction of 22.67%. These results have practical
implications for AI systems engineers using LLMs to solve real-world problems
with CoT prompt-engineering techniques. In addition, these results provide more
general insight for AI researchers studying the emergent behavior of
step-by-step reasoning in LLMs.

通过比较标准 CoT 和 CCoT 提示，我们介绍了简洁的思路链 (CCot) 提示，并评估了它对回答长度和正确答案准确性的影响。我们使用 GPT-3.5 和 GPT-4 在多项选择问答 (MCQA) 基准上进行了评估。CCoT 使得 GPT-3.5 和 GPT-4 的回答平均长度减少了 48.70%，对问题解决性能影响微乎其微。然而，在数学问题上，使用 CCoT 的 GPT-3.5 表现出了 27.69% 的性能惩罚。总体而言，CCoT 将每个标记的成本平均降低了 22.67%。这些结果对于使用 LLM 解决带有 CoT 提示工程技术的现实世界问题的 AI 系统工程师具有实际意义。此外，这些结果为研究 LLM 中逐步推理的新兴行为的 AI 研究人员提供了更普遍的见解。

大型语言模型中简明的思维链对问题解决的益处

The Benefits of a Concise Chain of Thought on Problem-Solving in Large  Language Models

Great successes have been reported using Reinforcement Learning from Human
Feedback (RLHF) to align large language models. Open-source preference datasets
and reward models have enabled wider experimentation beyond generic chat
settings, particularly to make systems more "helpful" for tasks like web
question answering, summarization, and multi-turn dialogue. When optimizing for
helpfulness, RLHF has been consistently observed to drive models to produce
longer outputs. This paper demonstrates that optimizing for response length is
a significant factor behind RLHF's reported improvements in these settings.
First, we study the relationship between reward and length for reward models
trained on three open-source preference datasets for helpfulness. Here, length
correlates strongly with reward, and improvements in reward score are driven in
large part by shifting the distribution over output lengths. We then explore
interventions during both RL and reward model learning to see if we can achieve
the same downstream improvements as RLHF without increasing length. While our
interventions mitigate length increases, they aren't uniformly effective across
settings. Furthermore, we find that even running RLHF with a reward based
solely on length can reproduce most of the downstream improvements over the
initial policy model, showing that reward models in these settings have a long
way to go.

通过针对回应长度进行优化，研究表明强化学习从人类反馈中能够取得显著的改进，该研究还探索了其他方法以在不增加长度的情况下实现模型性能的提升，并发现了回应长度在奖励模型方面的相关性。