Related papers: REALM: Reliable Expertise-Aware Language Model Fin…

One way to enhance the reasoning capability of Large Language Models (LLMs) is to conduct Supervised Fine-Tuning (SFT) using Chain-of-Thought (CoT) annotations. This approach does not show sufficiently strong generalization ability,…

Incorporating every annotator's perspective is crucial for unbiased data modeling. Annotator fatigue and changing opinions over time can distort dataset annotations. To combat this, we propose to learn a more accurate representation of…

Uncertainty in machine learning models is a timely and vast field of research. In supervised learning, uncertainty can already occur in the first stage of the training process, the annotation phase. This scenario is particularly evident…

Most reinforcement learning (RL) methods for training large language models (LLMs) require ground-truth labels or task-specific verifiers, limiting scalability when correctness is ambiguous or expensive to obtain. We introduce Reinforcement…

Machine learning models are routinely used to support decisions that affect individuals -- be it to screen a patient for a serious illness or to gauge their response to treatment. In these tasks, we are limited to learning models from…

Large language models (LLMs) often produce inaccurate or misleading content-hallucinations. To address this challenge, we introduce Noise-Augmented Fine-Tuning (NoiseFiT), a novel framework that leverages adaptive noise injection based on…

Learning from noisy labels is an important and long-standing problem in machine learning for real applications. One of the main research lines focuses on learning a label corrector to purify potential noisy labels. However, these methods…

Auto-annotation by ensemble of models is an efficient method of learning on unlabeled data. Wrong or inaccurate annotations generated by the ensemble may lead to performance degradation of the trained model. To deal with this problem we…

Generative large language models (LLMs) can be a powerful tool for augmenting text annotation procedures, but their performance varies across annotation tasks due to prompt quality, text data idiosyncrasies, and conceptual difficulty.…

Robustness to label noise within data is a significant challenge in federated learning (FL). From the data-centric perspective, the data quality of distributed datasets can not be guaranteed since annotations of different clients contain…

As Large Language Model (LLM) alignment evolves from simple completions to complex, highly sophisticated generation, Reward Models are increasingly shifting toward rubric-guided evaluation to mitigate surface-level biases. However, the…

Reinforcement Learning with Verifiable Rewards (RLVR) effectively trains reasoning models that rely on abundant perfect labels, but its vulnerability to unavoidable noisy labels due to expert scarcity remains critically underexplored. In…

Recently, Language Models (LMs) instruction-tuned on multiple tasks, also known as multitask-prompted fine-tuning (MT), have shown the capability to generalize to unseen tasks. Previous work has shown that scaling the number of training…

Visual planning asks a model to generate the remaining steps of a procedure in natural language given a partial video context and a goal. Progress on this task is bottlenecked by annotation: clean labeled datasets are small, domain-narrow,…

Recent pre-trained abstractive summarization systems have started to achieve credible performance, but a major barrier to their use in practice is their propensity to output summaries that are not faithful to the input and that contain…

Multi-annotator learning traditionally aggregates diverse annotations to approximate a single ground truth, treating disagreements as noise. However, this paradigm faces fundamental challenges: subjective tasks often lack absolute ground…

Fully-test-time adaptation (F-TTA) can mitigate performance loss due to distribution shifts between train and test data (1) without access to the training data, and (2) without knowledge of the model training procedure. In online F-TTA, a…

Retrieval-Augmented Language Models (RALMs) have demonstrated significant potential in knowledge-intensive tasks; however, they remain vulnerable to performance degradation when presented with irrelevant or noisy retrieved contexts.…

Fine-tuning Large Language Models (LLMs) typically relies on large quantities of high-quality annotated data, or questions with well-defined ground truth answers in the case of Reinforcement Learning with Verifiable Rewards (RLVR). While…

The growing need to analyze large collections of documents has led to great developments in topic modeling. Since documents are frequently associated with other related variables, such as labels or ratings, much interest has been placed on…