Summary of Large Language Models Are Inconsistent and Biased Evaluators, by Rickard Stureborg et al.
Large Language Models are Inconsistent and Biased Evaluators
by Rickard Stureborg, Dimitris Alikaniotis, Yoshi Suhara
First submitted to arxiv on: 2 May 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 This paper investigates the robustness and limitations of Large Language Model (LLM) evaluators, which are commonly used in Natural Language Processing (NLP) tasks. The authors analyze the SummEval dataset and find that LLMs exhibit biases such as familiarity bias, skewed distributions, anchoring effects, and inconsistency in evaluating text quality. They also provide recipes for configuring LLM evaluators to mitigate these limitations. Experimental results on the RoSE dataset demonstrate improvements over state-of-the-art LLM evaluators. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper looks at how well Large Language Models (LLMs) can judge the quality of text without any help or references. The researchers found that LLMs have some big flaws, like favoring familiar texts and not giving consistent scores. They also discovered that LLMs can be tricked by small changes in the way they’re asked to evaluate text. The authors give tips on how to make LLM evaluators better at what they do. |
Keywords
» Artificial intelligence » Large language model » Natural language processing » Nlp
