Related papers: Navigating the Synchrony-Stability Frontier in Ada…

In this paper, we aim to align large language models with the ever-changing, complex, and diverse human values (e.g., social norms) across time and locations. This presents a challenge to existing alignment techniques, such as supervised…

Modeling voice identity is challenging due to its multifaceted nature. In generative speech systems, identity is often assessed using automatic speaker verification (ASV) embeddings, designed for discrimination rather than characterizing…

While Large Language Models (LLMs) are widely documented to be sensitive to minor prompt perturbations and prone to sycophantic alignment, their robustness in consequential, rule-bound decision-making remains under-explored. We uncover a…

Large Language Models (LLMs) often experience performance degradation during long-running interactions due to increasing context length, memory saturation, and computational overhead. This paper presents an adaptive context compression…

LLMs enable qualitative coding at large scale, but assessing reliability remains challenging where human experts seldom agree. We investigate confidence-diversity calibration as a quality assessment framework for accessible coding tasks…

Large language models increasingly serve as conversational agents that adopt personas and role-play characters at user request. This capability, while valuable, raises concerns about sycophancy: the tendency to provide responses that…

Large Language Models (LLMs) increasingly prioritize user validation over epistemic accuracy - a phenomenon known as sycophancy. We present The Silicon Mirror, an orchestration framework that dynamically detects user persuasion tactics and…

At present, executable visual workflows have emerged as a mainstream paradigm in real-world industrial deployments, offering strong reliability and controllability. However, in current practice, such workflows are almost entirely…

In the context of Human-Robot Collaboration (HRC), it is crucial that the two actors are able to communicate with each other in a natural and efficient manner. The absence of a communication interface is often a cause of undesired…

We propose a novel preference alignment framework for improving spoken dialogue models on real-time conversations from user interactions. Current preference learning methods primarily focus on text-based language models, and are not…

Conventional seq2seq chatbot models attempt only to find sentences with the highest probabilities conditioned on the input sequences, without considering the sentiment of the output sentences. In this paper, we investigate four models to…

We present metrics for evaluating dialog systems through a psychologically-grounded "human" lens in which conversational agents express a diversity of both states (e.g., emotion) and traits (e.g., personality), just as people do. We present…

Standardized surveys scale efficiently but sacrifice depth, while conversational interviews improve response quality at the cost of scalability and consistency. This study bridges the gap between these methods by introducing a framework for…

The emergence of Generative AI (Gen AI) and Large Language Models (LLMs) has enabled more advanced chatbots capable of human-like interactions. However, these conversational agents introduce a broader set of operational risks that extend…

Emerging reports of the harms caused to children and adults by AI sycophancy and by parasocial ties with chatbots point to an urgent need for safeguards against such risks. Yet, preventing such dynamics is challenging: parasocial cues often…

Large language models (LLMs) are increasingly applied in educational, clinical, and professional settings, but their tendency for sycophancy -- prioritizing user agreement over independent reasoning -- poses risks to reliability. This study…

In this paper, we present a benchmark to pressure-test today's frontier models' multimodal decision-making capabilities in the very long-context regime (up to one million tokens) and investigate whether these models can learn from large…

Training large language models faces frequent interruptions due to various faults, demanding robust fault-tolerance. Existing backup-free methods, such as redundant computation, dynamic parallelism, and data rerouting, each incur…

Models trained on large unlabeled corpora of human interactions will learn patterns and mimic behaviors therein, which include offensive or otherwise toxic behavior and unwanted biases. We investigate a variety of methods to mitigate these…

We introduce \textsc{CAT}, a framework designed to evaluate and visualize the \emph{interplay} of \emph{accuracy} and \emph{response consistency} of Large Language Models (LLMs) under controllable input variations, using multiple-choice…