相关论文: Durkheim Project Data Analysis Report

Dynamic Link Prediction (DLP) addresses the prediction of future links in evolving networks. However, accurately portraying the performance of DLP algorithms poses challenges that might impede progress in the field. Importantly, common…

Large Language Models deployed as code generation agents exhibit stochastic behavior incompatible with the deterministic guarantees required by software engineering. We formalize the Dual-State Action Pair (DSAP), an execution primitive…

Speech patterns have been identified as potential diagnostic markers for neuropsychiatric conditions. However, most studies only compare a single clinical group to healthy controls, whereas clinical practice often requires differentiating…

While existing depression prediction methods based on deep learning show promise, their practical application is hindered by the lack of trustworthiness, as these deep models are often deployed as black box models, leaving us uncertain on…

Free association is a task that requires a subject to express the first word to come to their mind when presented with a certain cue. It is a task which can be used to expose the basic mechanisms by which humans connect memories. In this…

Autoregressive Large Language Models (LLMs) trained for next-word prediction have demonstrated remarkable proficiency at producing coherent text. But are they equally adept at forming coherent probability judgments? We use probabilistic…

Deep neural networks generalize well despite being heavily overparameterized, in apparent contradiction with classical learning theory based on uniform convergence over fixed hypothesis spaces. Uniform bounds over the entire parameter space…

As artificial agents become increasingly capable, what internal structure is *necessary* for an agent to act competently under uncertainty? Classical results show that optimal control can be *implemented* using belief states or world…

There have been many advances in the artificial intelligence field due to the emergence of deep learning. In almost all sub-fields, artificial neural networks have reached or exceeded human-level performance. However, most of the models are…

Paraphrasing re-expresses meaning to enhance applications like text simplification, machine translation, and question-answering. Specific paraphrase types facilitate accurate semantic analysis and robust language models. However, existing…

Large language models have shown impressive capabilities across a variety of NLP tasks, yet their generating text autoregressively is time-consuming. One way to speed them up is speculative decoding, which generates candidate segments (a…

Prediction-powered inference (PPI) is a method that improves statistical estimates based on limited human-labeled data. PPI achieves this by combining small amounts of human-labeled data with larger amounts of data labeled by a reasonably…

Decision-makers are faced with the challenge of estimating what is likely to happen when they take an action. For instance, if I choose not to treat this patient, are they likely to die? Practitioners commonly use supervised learning…

We propose a method that integrates supervised extractive and generative language models for providing supporting evidence of suicide risk in the CLPsych 2024 shared task. Our approach comprises three steps. Initially, we construct a…

While alignment algorithms are now commonly used to tune pre-trained language models towards a user's preferences, we lack explanations for the underlying mechanisms in which models become ``aligned'', thus making it difficult to explain…

Conversational agents have become an integral part of the general population for simple task enabling situations. However, these systems are yet to have any social impact on the diverse and minority population, for example, helping people…

The massive collection of user posts across social media platforms is primarily untapped for artificial intelligence (AI) use cases based on the sheer volume and velocity of textual data. Natural language processing (NLP) is a subfield of…

This paper develops a new approach to post-selection inference for screening high-dimensional predictors of survival outcomes. Post-selection inference for right-censored outcome data has been investigated in the literature, but much…

The amount of freely available systems for automatic speech recognition (ASR) based on neural networks is growing steadily, with equally increasingly reliable predictions. However, the evaluation of trained models is typically exclusively…

Extracting structured information from clinical notes requires navigating a dense web of interdependent variables where the value of one attribute logically constrains others. Existing Large Language Model (LLM)-based extraction pipelines…