Nandini Maroo supervised by Dr. Kavita Vemuri received her Master of Science – Dual Degree in Computer Science and Engineering (CSD). Here’s a summary of her research work on Social Ties in Strategic Reasoning: Selective Use in Humans Versus Generalized Use in Language Models

People and large language models both respond to social relationships, but they do so in different ways. Studies of social distance in economic games show mixed results: some find that people treat close others more generously, while others find no effect. This thesis argues that this inconsistency reflects a structural principle: social ties influence behavior only when the task requires reasoning about a specific person, and not when shared norms already guide decisions. This account is tested in humans and in large language models. Study 1 examined naturally occurring dyads with no tie, weak tie, or strong tie. Participants played three economic games: Dictator, Ultimatum, and Centipede. At each decision, participants also reported their beliefs about their coplayer. Tie strength did not change offers or beliefs in the Dictator or Ultimatum games, both of which involve strong fairness expectations that apply regardless of the relationship between players. In the Centipede Game, strong-tie pairs cooperated 1.47 rounds longer than no-tie pairs and expected co-players to stop 1.14 rounds later. Both effects remained significant after multiple-comparison correction. Beliefs predicted behavior across all groups, and strong ties predicted longer cooperation even after controlling for observer expectations. Study 2 tested two large language models, Mistral 7B Instruct and Llama 3 8B Instruct, on the same three games. Prompts varied the tie label, behavioral history, and history type in a full factorial design across thousands of trials. The selective pattern found in humans was not observed in the models. Tie effects were present across all three games for both models, with no concentration in the task where predicting a specific partner is most important. Notably, the social tie effect in the Dictator Game (η²ₚ = .137 for LLaMA Action) was larger than in the Centipede Game (η²ₚ = .030). This indicates a failure of selectivity rather than a lack of sensitivity to social cues. Relational language appears to function as a general cooperative bias rather than information used only when it is strategically relevant. Llama 3 8B showed larger and more consistent tie effects than Mistral 7B, likely reflecting alignment training rather than stronger relational reasoning. Humans and current language models therefore differ not in whether they respond to social ties, but in how they use them. Humans apply relational knowledge selectively, using it where shared norms do not provide a clear script and partner-specific reasoning is needed. Models apply relational cues more broadly, regardless of whether the task makes them useful. These findings show that social reasoning in humans is sensitive to task structure, while in current models it operates as a more general bias, highlighting a key difference that warrants further investigation. 

June 2026