Related papers: Social Comparison without Explicit Inference of Ot…

Machine learning is often viewed as an inherently value-neutral process: statistical tendencies in the training inputs are "simply" used to generalize to new examples. However when models impact social systems such as interactions between…

Indirect reciprocity explains the evolution of cooperation by considering how our cooperative behavior toward someone is reciprocated by someone else who has observed us. A cohesive society has a shared norm that prescribes how to assess…

Conflict destabilizes social interactions and impedes cooperation at multiple scales of biological organization. Of fundamental interest are the causes of turbulent periods of conflict. We analyze conflict dynamics in a monkey society model…

When a robot learns from human examples, most approaches assume that the human partner provides examples of optimal behavior. However, there are applications in which the robot learns from non-expert humans. We argue that the robot should…

Image generation models are poised to become ubiquitous in a range of applications. These models are often fine-tuned and evaluated using human quality judgments that assume a universal standard, failing to consider the subjectivity of such…

Machine learning systems have been widely used to make decisions about individuals who may behave strategically to receive favorable outcomes, e.g., they may genuinely improve the true labels or manipulate observable features directly to…

An important aspect of human conversation difficult for machines is conversing with empathy, which is to understand the user's emotion and respond appropriately. Recent neural conversation models that attempted to generate empathetic…

The task of ranking individuals or teams, based on a set of comparisons between pairs, arises in various contexts, including sporting competitions and the analysis of dominance hierarchies among animals and humans. Given data on which…

Indirect reciprocity is a foundational mechanism of human cooperation. Existing models of indirect reciprocity fail to robustly support social cooperation: image scoring models fail to provide robust incentives, while social standing models…

Emotions play a critical role in our everyday lives by altering how we perceive, process and respond to our environment. Affective computing aims to instill in computers the ability to detect and act on the emotions of human actors. A core…

Large language models (LLMs) reflect societal norms and biases, especially about gender. While societal biases and stereotypes have been extensively researched in various NLP applications, there is a surprising gap for emotion analysis.…

For many tasks, the reward function is inaccessible to introspection or too complex to be specified procedurally, and must instead be learned from user data. Prior work has evaluated learned reward functions by evaluating policies optimized…

Negative emotions are linked to the onset of neurodegenerative diseases and dementia, yet they are often difficult to detect through observation. Physiological signals from wearable devices offer a promising noninvasive method for…

As large language models (LLMs) increasingly engage in complex social interactions, ensuring that their behaviors align with human ethical principles and intentions, known as value alignment, has become a critical scientific challenge.…

We explore unconstrained natural language feedback as a learning signal for artificial agents. Humans use rich and varied language to teach, yet most prior work on interactive learning from language assumes a particular form of input (e.g.,…

Recent research has devoted considerable effort to verifying the intermediate reasoning steps of chain-of-thought (CoT) trajectories using process reward models (PRMs) and other verifier models. However, training a PRM typically requires…

Humans are interactive agents driven to seek out situations with interesting physical dynamics. Here we formalize the functional form of physical intrinsic motivation. We first collect ratings of how interesting humans find a variety of…

Humans do not always make rational choices, a fact that experimental economics is putting on solid grounds. The social context plays an important role in determining our actions, and often we imitate friends or acquaintances without any…

Reward models are a key component of large language model alignment, serving as proxies for human preferences during training. However, existing evaluations focus primarily on broad instruction-following benchmarks, providing limited…

Large language models (LLMs) are increasingly deployed via public-facing interfaces to interact with millions of users, each with diverse preferences. Despite this, preference tuning of LLMs predominantly relies on reward models trained…