Large Language Models as Biomedical Hypothesis Generators: A Comprehensive Evaluation

Summary

The paper evaluates the large language model's ability as a biomedical hypothesis generator. It starts by constructing background hypothesis pairs from biomedical literature and splitting the test sets based on publication date to mitigate data leakage. The paper then assesses the hypothesis generation capabilities of the state-of-the-art models in the zero-shot, few-shot, and fine-tuning settings. It conducts both automatic and human evaluations. The experiment shows several impacts of external knowledge. The paper also builds a multi-agent framework for hypothesis generation and refinement. Specifically, the paper constructs four roles including analyst, engineer, scientist, and critic. The paper also tests tool learning.

Rating

7

Confidence

4

Ethics flag

1

Reasons to accept

1. The paper proposes an interesting and useful task for generating biomedical hypotheses. To avoid data leakage, it also constructs a new dataset with 2,700 seen and 200 unseen subsets. The paper also proposes a new multi-agent hypothesis generation framework for analyzing human scientific collaboration. The multi-agent framework design is intuitive. 2. The paper conducts a comprehensive evaluation. When analyzing LLMs' ability to generate hypotheses, it mainly compares three types of state-of-the-art models: API-based LLMs, open-source LLMs, and medical domain LLMs. The paper tests those models under zero-shot, few-shot, and fine-tuning. It analyzes the generation results with traditional metrics and ChatGPT and also conducts human evaluations. The paper reports human evaluation interannotator coefficient and its correlation with ChatGPT. 3. The visualizations of the results are clear and straightforward. The paper provides additional generation results and experiment details in the appendix. The paper also provides some interesting experiments insights about external knowledge.

Reasons to reject

1. Some details of the paper are unclear. It seems that the assumption and the background pairs are generated by GPT4. While the authors admit that manual annotation of a subset could help reflect the quality of the dataset, the paper fails to provide any manual evaluation of the constructed data. Additionally, the dataset seems to be a little bit small(with 200 pairs for testing). What does the 5shot* mean? Does it mean similarity retrieval-based few-shot? The fonts in Figure 5 are too small. The title of section 3 needs to be updated since it also analyzes few-shot and fine-tuning settings. 2. While the paper also evaluates the performance of multi-agent and tool use, the analysis part is superficial compared to section 3. The paper claims that adding a tool can further enhance the multi-agent. However, its performance on relevance and verifiability dropped. Additionally, the average score is also worse. 3. The external knowledge part focuses on the few-shot part. It might be more useful to include some external knowledge graph in the experiment to further strengthen this section's analysis.

Questions to authors

1. What are the sources of the dataset? 2. What are the quality of the dataset?

Summary

The authors present a comprehensive evaluation of large language models (LLMs) as biomedical hypothesis generators. By constructing a novel temporal dataset of background-hypothesis pairs and employing innovative experimental setups, they provide valuable insights into the capabilities of LLMs in zero-shot and few-shot settings. The authors also propose a tool-augmented/multi-agent framework and multidimensional evaluation metrics, which seem to contribute to a deeper understanding of the factors influencing LLM-based hypothesis generation. Additionally, they explore the role of uncertainty and demonstrate that increasing uncertainty through tool use and multi-agent interactions can enhance the diversity and quality of generated hypotheses.

Rating

8

Confidence

4

Ethics flag

1

Reasons to accept

1. **Comprehensive evaluation of LLMs in zero-shot and few-shot hypothesis generation**: The authors create a novel temporal biomedical instruction dataset and conduct innovative experiments to thoroughly analyze and evaluate the performance of LLMs in generating hypotheses. The findings reveal that LLMs exhibit foundational higher-order reasoning capabilities and can generate novel hypotheses, offering fresh empirical insights for knowledge discovery in the biomedical domain. 2. **Uncertainty on hypothesis generation**: The authors explore the role of uncertainty in hypothesis generation by incorporating tool use and multi-agent interactions. They find that increasing uncertainty through these methods can facilitate diverse candidate generation and improve zero-shot hypothesis generation performance. 3. **Contribution in the biomedical domain**: The paper conducts a thorough evaluation of LLMs, specifically in the context of biomedical hypothesis generation, providing valuable insights and a foundation for future research in this domain.

Reasons to reject

1. **Design of evaluation metrics for evaluation without ground truth**: The paper lacks sufficient details and validation regarding the design of the four evaluation metrics. 2. **Tool use**: The authors directly employ the tool sets from ReAct and OpenAI to conclude that tool use does not significantly help with hypothesis generation. However, it is expected that general-domain tools would provide limited contributions. 3. **Role of the multi-agent framework**: It may lack ablation studies to evaluate the individual contributions and necessity of each role within the multi-agent framework.

Questions to authors

1. **Protocol and standards for human evaluation**: The authors conduct human evaluations to assess the coherence of hypotheses generated by LLMs and compare them with GPT-4 evaluation scores. However, the paper would benefit from providing more details regarding the protocol and standards followed during the human evaluation process. This additional information would help readers better understand the methodology and ensure the reproducibility of the human evaluation results. 2. **Analysis of the case study**: The case study section presents a list of tables containing generated hypotheses from various models. While this information is valuable, the lack of detailed analysis accompanying the tables may confuse readers. To improve clarity and enhance the readers' understanding, the authors should provide a more thorough analysis of the case study results.

Ethics concerns details

N/A

Summary

This paper proposed a novel dataset with rigorous curation, as well as some interesting/new metrics to evaluate/test the quality of the hypothesis of biofield. The authors used both human assessment and GPT-4 assessment in their evaluation. Many interesting discoveries were revealed and discussed, which will inform the community in the long term.

Rating

7

Confidence

4

Ethics flag

1

Reasons to accept

1. Authors curate a dataset of background hypothesis pairs from biomedical papers and classify them into training, seen, and unseen partitions based on their publication date to avoid the papers potentially included in LLM's pretraining. This will help test the generalization ability of LLMs. This dataset will inform the community in the long term. 2. There are many baselines studied. Various baselines are based on different LLMs as well as different ICL methods, from agent-based baselines to tool-based baselines. 3. One of the interesting discoveries about the alignment of AI feedback and human assessment shows a strong correlation, signaling that incorporating LLMs into hypothesis generation is possible.

Reasons to reject

1. Dataset validation and cleaning. Based on Figure 1, it seems that most of the curation is made by GPT-4, and human intervention is not very much involved. This might somehow bring bias and it might be useful to have human annotators to evaluate the error and bias rate. 2. Minor point: qualitative studies might be included to have a better sense of the alignment of human assessment and LLMs, in the cases where they agree and they disagree.

Questions to authors

1. Most of the baselines of Table 1 focus on not most advanced models. There are many other state of the art, for example, Mistral MOE models. Is there a reason for this choice?

Summary

This work explores the use of large language models (LLMs) in generating hypotheses for biomedical research. It introduces a novel dataset specifically designed to avoid data contamination and assesses these models across various settings, including zero-shot and few-shot scenarios, using several quantitative metrics to evaluate the quality of the generated hypotheses. Methodologically, it integrates 'tool use' and multi-agent interactions to determine how these approaches can enhance the hypothesis generation capabilities of LLMs. The results indicate that LLMs can, to some extent, generate relevant hypotheses, which could potentially accelerate biomedical research and discovery.

Rating

6

Confidence

4

Ethics flag

1

Reasons to accept

The work introduces a relevant resources for future research, and conduct several evaluation that may serve as starting point for more detailed analyses.

Reasons to reject

Overall, the paper could benefit from a more stricter contextualisation and focus, given the challenging nature of the tasks. - First, the work would benefit from a more detailed analysis of the types of hypotheses that LLMs can generate from a biomedical perspective, rather than just assessing the general quality of the hypotheses. This would better demonstrate the models' generalisation across various biomedical research scenarios. - The discussion about 'dark knowledge' is vaguely defined and poorly explained, leaving readers uncertain about its relevance and impact on hypothesis generation, and the strength of the supporting evidence for such statements. - Additionally, the discussion on uncertainty and the rationale behind certain evaluation metrics and frameworks, like SelfBLEU and the agent-based framework, is overly general and not well-supported, limiting the reliability of the evaluation process. - Lastly, a more elaborated analysis that explicitly compares this contribution with existing literature would better contextualize and strengthen the novelty of the proposed approaches.

Thank you for your response

I acknowledge that I have read the responses by the authors and I will keep my positive score.

Response to authors' rebuttal

Thanks for your clarification! You have addressed all of my concerns. I have read it carefully and decided to keep my positive score.

reponse

thanks authors for the response, and I remain positive about the paper.