Selfish routing begets inefficiency in multi-agent transportation systems, leading to significant economic losses in our society. Although several powerful techniques (e. g., marginal cost pricing) have been proposed to mitigate price-of-anarchy (a measure of inefficiency), social welfare maximization still remains a huge challenge in selfish routing, especially when travelers deviate from maximizing their own expected utilities. This paper proposes a novel informational intervention to improve the efficiency of selfish routing, especially in the presence of quantal response travelers. Specifically, modeling the interaction between the system and travelers as a Stackelberg game, and develop a novel approximate algorithm, called LoRI (which stands for logit response based information) to steer the travelers' logit responses towards social welfare using strategically designed information. Simulation results in diverse transportation settings demonstrate that LoRI significantly improves price of anarchy of selfish routing (both in terms of congestion and carbon emissions), even when the travelers use navigation services that recommend optimal shortest-paths according to their selfish interests.