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

@article{chadimova-2026-meaningless, author = {Milena Chadimov\'{a} and Eduard Jur\'{a}sek and Tom\'{a}s Kliegr}, title = {{Meaningless is better: Hashing bias-inducing words in LLM prompts improves performance in logical reasoning and statistical learning}}, journal = {Information Processing and Management}, volume = {63}, number = {3}, pages = {104493}, year = {2026}, url = {https://doi.org/10.1016/J.IPM.2025.104493}, doi = {https://doi.org/10.1016/J.IPM.2025.104493} }