# Meaningless is better: hashing bias-inducing words in LLM prompts improves performance in logical reasoning and statistical learning

arXiv: https://arxiv.org/abs/2411.17304 · HTML: https://mlsanity.com/paper/2411.17304/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning.
- Builds on 19 of its 47 references that are in the map.
- First posted on arXiv 26 Nov 2024.

## Placed in

- LLM reasoning / [Reasoning benchmarks and evaluation](https://mlsanity.com/lr/reasoning-benchmarks-and-evaluation/)

## Builds on (most cited first, 19 of 19)

- [TruthfulQA: Measuring How Models Mimic Human Falsehoods](https://mlsanity.com/paper/2109.07958/) (2021)
- [Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models](https://mlsanity.com/paper/2206.04615/) (2022)
- [A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions](https://mlsanity.com/paper/2311.05232/) (2023)
- [StereoSet: Measuring stereotypical bias in pretrained language models](https://mlsanity.com/paper/2004.09456/) (2020)
- [Thinking Fast and Slow in Large Language Models](https://mlsanity.com/paper/2212.05206/) (2022)
- [How well do Large Language Models perform in Arithmetic tasks?](https://mlsanity.com/paper/2304.02015/) (2023)
- [Table Meets LLM: Can Large Language Models Understand Structured Table Data? A Benchmark and Empirical Study](https://mlsanity.com/paper/2305.13062/) (2023)
- [CogBench: a large language model walks into a psychology lab](https://mlsanity.com/paper/2402.18225/) (2024)
- [Do Large Language Models Show Decision Heuristics Similar to Humans? A Case Study Using GPT-3.5](https://mlsanity.com/paper/2305.04400/) (2023)
- [Good at captioning, bad at counting: Benchmarking GPT-4V on Earth observation data](https://mlsanity.com/paper/2401.17600/) (2024)
- [(Ir)rationality and Cognitive Biases in Large Language Models](https://mlsanity.com/paper/2402.09193/) (2024)
- [A review of possible effects of cognitive biases on the interpretation of rule-based machine learning models](https://mlsanity.com/paper/1804.02969/) (2018)
- [Cognitive Effects in Large Language Models](https://mlsanity.com/paper/2308.14337/) (2023)
- [Assessing GPT4-V on Structured Reasoning Tasks](https://mlsanity.com/paper/2312.11524/) (2023)
- [Will the Real Linda Please Stand up...to Large Language Models? Examining the Representativeness Heuristic in LLMs](https://mlsanity.com/paper/2404.01461/) (2024)
- [Recovering from Privacy-Preserving Masking with Large Language Models](https://mlsanity.com/paper/2309.08628/) (2023)
- [LLM Cognitive Judgements Differ From Human](https://mlsanity.com/paper/2307.11787/) (2023)
- [Problematic Tokens: Tokenizer Bias in Large Language Models](https://mlsanity.com/paper/2406.11214/) (2024)
- [Word Importance Explains How Prompts Affect Language Model Outputs](https://mlsanity.com/paper/2403.03028/) (2024)

## Built on by (most cited first, 1 of 1)

- [Meaningless Tokens, Meaningful Gains: How Activation Shifts Enhance LLM Reasoning](https://mlsanity.com/paper/2510.01032/) (2025)

## Abstract (arXiv)

This paper introduces a novel method, referred to as "hashing", which involves masking potentially bias-inducing words in large language models (LLMs) with hash-like meaningless identifiers to reduce cognitive biases and reliance on external knowledge. The method was tested across three sets of experiments involving a total of 490 prompts. Statistical analysis using chi-square tests showed significant improvements in all tested scenarios, which covered LLama, ChatGPT, Copilot, Gemini and Mixtral models. In the first experiment, hashing decreased the fallacy rate in a modified version of the "Linda" problem aimed at evaluating susceptibility to cognitive biases. In the second experiment, it improved LLM results on the frequent itemset extraction task. In the third experiment, we found hashing is also effective when the Linda problem is presented in a tabular format rather than text, indicating that the technique works across various input representations. Overall, the method was shown to improve bias reduction and incorporation of external knowledge. Despite bias reduction, hallucination rates were inconsistently reduced across types of LLM models. These findings suggest that masking bias-inducing terms can improve LLM performance, although its effectiveness is model- and task-dependent.