Related papers: Robust Uncertainty Quantification for Self-Evolvin…

Recent Multimodal Large Language Models (MLLMs) excel in vision-language understanding but face challenges in adapting to dynamic real-world scenarios that require continuous integration of new knowledge and skills. While continual learning…

Consistency, which refers to the capability of generating the same predictions for semantically similar contexts, is a highly desirable property for a sound language understanding model. Although recent pretrained language models (PLMs)…

Despite the impressive capability of large language models (LLMs), knowing when to trust their generations remains an open challenge. The recent literature on uncertainty quantification of natural language generation (NLG) utilises a…

Recent advances in domain adaptation show that deep self-training presents a powerful means for unsupervised domain adaptation. These methods often involve an iterative process of predicting on target domain and then taking the confident…

Counterfactual learning to rank (CLTR) has attracted extensive attention in the IR community for its ability to leverage massive logged user interaction data to train ranking models. While the CLTR models can be theoretically unbiased when…

Conformal Prediction (CP) serves as a robust framework that quantifies uncertainty in predictions made by Machine Learning (ML) models. Unlike traditional point predictors, CP generates statistically valid prediction regions, also known as…

Accurately gauging the confidence level of Large Language Models' (LLMs) predictions is pivotal for their reliable application. However, LLMs are often uncalibrated inherently and elude conventional calibration techniques due to their…

Effective protein representation learning is crucial for predicting protein functions. Traditional methods often pretrain protein language models on large, unlabeled amino acid sequences, followed by finetuning on labeled data. While…

We investigate the predictability of large language model (LLM) capabilities: given records of past experiments using different model families, numbers of parameters, tasks, and numbers of in-context examples, can we accurately predict LLM…

Since the inception of Large Language Models (LLMs), the quest to efficiently train them for superior reasoning capabilities has been a pivotal challenge. The dominant training paradigm for LLMs is based on next token prediction (NTP).…

Self-training approach for large language models (LLMs) improves reasoning abilities by training the models on their self-generated rationales. Previous approaches have labeled rationales that produce correct answers for a given question as…

Conformal prediction (CP) is a wrapper around traditional machine learning models, giving coverage guarantees under the sole assumption of exchangeability; in classification problems, for a chosen significance level $\varepsilon$, CP…

Contrastive representation learning (CRL) underpins many modern foundation models. Despite recent theoretical progress, existing analyses suffer from several key limitations: (i) the statistical consistency of CRL remains poorly understood;…

As LLMs evolve, significant effort is spent on manually crafting prompts. While existing prompt optimization methods automate this process, they rely solely on learning from incorrect samples, leading to a sub-optimal performance.…

Protein language models (pLMs) have recently gained significant attention for their ability to uncover relationships between sequence, structure, and function from evolutionary statistics, thereby accelerating therapeutic drug discovery.…

Continual learning (CL) is concerned with learning multiple tasks sequentially without forgetting previously learned tasks. Despite substantial empirical advances over recent years, the theoretical development of CL remains in its infancy.…

Conformal prediction (CP) is a powerful framework for quantifying uncertainty in machine learning models, offering reliable predictions with finite-sample coverage guarantees. When applied to classification, CP produces a prediction set of…

Adapting general large language models (LLMs) to specialized domains presents great challenges due to varied data distributions. This adaptation typically requires continual pre-training on massive domain-specific corpora to facilitate…

Continual learning (CL) refers to the ability to continuously learn and accumulate new knowledge while retaining useful information from past experiences. Although numerous CL methods have been proposed in recent years, it is not…

A continual learning (CL) algorithm learns from a non-stationary data stream. The non-stationarity is modeled by some schedule that determines how data is presented over time. Most current methods make strong assumptions on the schedule and…