Related papers: Working Notes on Late Interaction Dynamics: Analyz…

With the widespread adoption of Large Language Models (LLMs), the prevalence of iterative interactions among these models is anticipated to increase. Notably, recent advancements in multi-round self-improving methods allow LLMs to generate…

Multimodal retrieval systems are expected to operate in a semantic space, agnostic to the language or cultural origin of the query. In practice, however, retrieval outcomes systematically reflect perspectival biases: deviations shaped by…

Large language models (LLMs) are increasingly deployed in decision-support systems for high-stakes domains such as hiring and university admissions, where choices often involve selecting among competing alternatives. While prior work has…

Modeling coordination among generative agents in complex multi-round decision-making presents a core challenge for AI and operations management. Although behavioral experiments have revealed cognitive biases behind supply chain…

Mixed effects regression models are widely used by language researchers. However, these regressions are implemented with an algorithm which may not converge on a solution. While convergence issues in linear mixed effects models can often be…

Multi-task post-training of large language models (LLMs) is typically performed by mixing datasets from different tasks and optimizing them jointly. This approach implicitly assumes that all tasks contribute gradients of similar magnitudes;…

We propose Love First, Know Later: a paradigm shift in computational matching that simulates interactions first, then assesses compatibility. Instead of comparing static profiles, our framework leverages LLMs as text world engines that…

The rapid advancement of large language models (LLMs) has led to growing interest in using synthetic data to train future models. However, this creates a self-consuming retraining loop, where models are trained on their own outputs and may…

Recent works have shown considerable improvements in task-oriented dialogue (TOD) systems by utilizing pretrained large language models (LLMs) in an end-to-end manner. However, the biased behavior of each component in a TOD system and the…

Reinforcement Learning (RL) agents often struggle with inefficient exploration, particularly in environments with sparse rewards. Traditional exploration strategies can lead to slow learning and suboptimal performance because agents fail to…

Personalisation is a standard feature of conversational AI systems used by millions; yet, the efficacy of personalisation methods is often evaluated in academic research using simulated users rather than real people. This raises questions…

Multimodal Large Language Models (MLLMs) utilize multimodal contexts consisting of text, images, or videos to solve various multimodal tasks. However, we find that changing the order of multimodal input can cause the model's performance to…

Latent factor models are increasingly popular for modeling multi-relational knowledge graphs. By their vectorial nature, it is not only hard to interpret why this class of models works so well, but also to understand where they fail and how…

Large Language Models (LLMs) have shown powerful performance and development prospects and are widely deployed in the real world. However, LLMs can capture social biases from unprocessed training data and propagate the biases to downstream…

As autonomous agents become more prevalent, understanding their collective behaviour in strategic interactions is crucial. This study investigates the emergent cooperative tendencies of systems of Large Language Model (LLM) agents in a…

We investigate the impact of search strategies in neural dialogue modeling. We first compare two standard search algorithms, greedy and beam search, as well as our newly proposed iterative beam search which produces a more diverse set of…

Enabling robots to learn novel visuomotor skills in a data-efficient manner remains an unsolved problem with myriad challenges. A popular paradigm for tackling this problem is through leveraging large unlabeled datasets that have many…

In causal matching designs, some control subjects are often left unmatched, and some covariates are often left unmodeled. This article introduces "rebar," a method using high-dimensional modeling to incorporate these commonly discarded data…

Large Language Models (LLMs) are increasingly used for synthetic tabular data generation through in-context learning (ICL), offering a practical solution for data augmentation in data scarce scenarios. While prior work has shown the…

Understanding how adult humans learn non-native speech categories such as tone information has shed novel insights into the mechanisms underlying experience-dependent brain plasticity. Scientists have traditionally examined these questions…