文学选的交互式主动学习:微调GPT与DeepSeek的推理,以实现跨领域的概括
Yiming Li1,2, Joseph M Plasek1,2, Xinsong Du1,2
1Department of Medicine, Harvard Medical School, Boston, MA 02115, United States.
概括
本研究介绍了一种主动学习框架,该框架利用大型语言模型 (LLM) 之间的分歧来改善生物医学文献选. 使用这种方法微调的GPT模型显著提高了性能,特别是在像GPT-4o-mini.等更轻的模型中.
科学领域:
- 生物医学信息学 生物医学信息学
- 人工智能在医学中的应用
背景情况:
- 生物医学领域的自动化文献选面临来自领域转移和有限的标记数据的挑战.
- 大型语言模型 (LLM) 在零射击设置中与复杂的,域特定的推理作斗争.
研究的目的:
- 调查一个交互式,弱监督的学习框架,将GPT的微调与DeepSeek的推理结合起来,以改善生物医学文献选.
- 为了提高模型的准确性和可泛化性在不同的生物医学领域.
主要方法:
- 开发了一个主动学习框架,使用GPT-4o和DeepSeek之间的模型分歧来识别错误分类的文章.
- 使用基于分歧的样本和DeepSeek的弱监管逻辑痕迹,微调了三种GPT变体 (GPT-4o,GPT-4o-mini,GPT-4.1-nano).
- 评估了癌症免疫疗法和医学LLM的独立基准集的性能,优先考虑召回.
主要成果:
- 微调GPT模型以基于不同意见的示例显著提高了性能.
- 在微调后,GPT-4o-mini获得了最高的F1得分 (0.93) 和召回 (0.95).
- 精心调整的模型在生物医学主题中始终优于零射击对手,而不会增加审查员的工作量.
结论:
- 基于分歧的积极学习有效地提高了基于GPT的生物医学文献选.
- 像GPT-4o-mini这样的轻量级模型显示了有针对性,推理丰富的培训带来的显著好处.
- 该框架提供了一个可扩展的解决方案,用于在系统审查中有效和可靠地检索信息.
相关概念视频
Genetic Screens
5.8K
Genetic screens are tools used to identify genes and mutations responsible for phenotypes of interest. Genetic screens help identify individuals or a group of people at risk of developing genetic diseases and help them with early intervention, targeted therapy, and reproductive options.
Forward genetic screens
Forward or “classical” genetic screens involve creating random mutations in an organism’s DNA using radiation, mutagens, or insertion of additional bases, which...
Forward genetic screens
Forward or “classical” genetic screens involve creating random mutations in an organism’s DNA using radiation, mutagens, or insertion of additional bases, which...
5.8K
Purposive Learning
558
E. C. Tolman emphasized the purposiveness of behavior — the idea that much of our behavior is goal-directed. For instance, employees who aim for a promotion work diligently to meet their targets. Tolman argued that when classical conditioning and operant conditioning occur, the organism acquires certain expectations. In classical conditioning, a child might fear a dog because they expect it to bite. In operant conditioning, a person might consistently work overtime because they expect a...
558
Inductive Reasoning
69.0K
Inductive reasoning is a form of logical thinking that uses related observations to arrive at a general conclusion. It is uncertain and operates in degrees to which the conclusions are credible. As such, inductive arguments can be weak or strong, rather than valid or invalid, and conclusions can be used to formulate testable, falsifiable hypotheses.
Inductive reasoning is common in descriptive science. A life scientist makes observations and records them. This data can be qualitative or...
Inductive reasoning is common in descriptive science. A life scientist makes observations and records them. This data can be qualitative or...
69.0K
Critical Thinking II
5.2K
Critical thinking is a cognitive process with several attributes. The attributes of critical thinking include the following:
5.2K
Reasoning
487
Reasoning is the action of thinking about something in a logical, sensible way. It is integral to problem-solving, decision-making, and critical thinking. Reasoning can be inductive or deductive. Reasoning involves transforming information into conclusions, which is essential for problem-solving, decision-making, and critical thinking.
Inductive reasoning involves deriving generalizations from specific observations. This type of reasoning helps form beliefs about the world. For example,...
Inductive reasoning involves deriving generalizations from specific observations. This type of reasoning helps form beliefs about the world. For example,...
487
Deductive Reasoning
71.3K
Deductive reasoning, or deduction, is the type of logic used in hypothesis-based science. In deductive reasoning, the pattern of thinking moves in the opposite direction as compared to inductive reasoning, which means that it uses a general principle or law to predict specific results. From those general principles, a scientist can deduce and predict the specific results that would be valid as long as the general principles are valid.
For example, a researcher can deduce specific predictions...
For example, a researcher can deduce specific predictions...
71.3K

