Summary of Ai Can Be Cognitively Biased: An Exploratory Study on Threshold Priming in Llm-based Batch Relevance Assessment, by Nuo Chen et al.
AI Can Be Cognitively Biased: An Exploratory Study on Threshold Priming in LLM-Based Batch Relevance Assessment
by Nuo Chen, Jiqun Liu, Xiaoyu Dong, Qijiong Liu, Tetsuya Sakai, Xiao-Ming Wu
First submitted to arxiv on: 24 Sep 2024
Categories
- Main: Computation and Language (cs.CL)
- Secondary: Artificial Intelligence (cs.AI)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary Cognitive biases in large language models (LLMs) have been explored for their social biases, but the broader impact of these biases on decision-making remains underexplored. This study investigates whether LLMs are influenced by the threshold priming effect in relevance judgments, a widely-discussed topic in Information Retrieval (IR). The experiment employed 10 topics from the TREC 2019 Deep Learning passage track collection and tested AI judgments under different document relevance scores, batch lengths, and LLM models. Results showed that LLMs tend to give lower scores to later documents if earlier ones have high relevance, and vice versa, regardless of the combination and model used. This finding demonstrates that LLMs’ judgments are influenced by threshold priming biases, similar to human judgments, suggesting that researchers and engineers should consider cognitive biases in designing, evaluating, and auditing LLMs in IR tasks and beyond. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Large language models can make mistakes because they learn from humans who have biases. This study looked at whether these language models also have a problem called the threshold priming effect. Imagine you’re searching for information online and you see some results that are really good, then you start to think the next set of results will be less good. That’s kind of what this study found happened with the language models. They gave lower scores to later documents if earlier ones had high relevance, and vice versa. This means we need to consider these biases when building and testing these language models. |
Keywords
* Artificial intelligence * Deep learning
