Skip to main content

🟢 Introduction

This chapter covers how to make completions more reliable, as well as how to implement checks to ensure that outputs are reliable.

To a certain extent, most of the previous techniques covered have to do with improving completion accuracy, and thus reliability, in particular self-consistency1. However, there are a number of other techniques that can be used to improve reliability, beyond basic prompting strategies.

LLMs have been found to be more reliable than we might expect at interpreting what a prompt is trying to say when responding to misspelled, badly phrased, or even actively misleading prompts2. Despite this ability, they still exhibit various problems including hallucinations3, flawed explanations with CoT methods3, and multiple biases including majority label bias, recency bias, and common token bias4. Additionally, zero-shot CoT can be particularly biased when dealing with sensitive topics5.

Common solutions to some of these problems include calibrators to remove a priori biases, and verifiers to score completions, as well as promoting diversity in completions.

  1. Wang, X., Wei, J., Schuurmans, D., Le, Q., Chi, E., Narang, S., Chowdhery, A., & Zhou, D. (2022). Self-Consistency Improves Chain of Thought Reasoning in Language Models. ↩
  2. Webson, A., Loo, A. M., Yu, Q., & Pavlick, E. (2023). Are Language Models Worse than Humans at Following Prompts? It’s Complicated. arXiv:2301.07085v1 [Cs.CL]. ↩
  3. Ye, X., & Durrett, G. (2022). The Unreliability of Explanations in Few-shot Prompting for Textual Reasoning. ↩
  4. Zhao, T. Z., Wallace, E., Feng, S., Klein, D., & Singh, S. (2021). Calibrate Before Use: Improving Few-Shot Performance of Language Models. ↩
  5. Shaikh, O., Zhang, H., Held, W., Bernstein, M., & Yang, D. (2022). On Second Thought, Let’s Not Think Step by Step! Bias and Toxicity in Zero-Shot Reasoning. ↩