-
2024Assessing the factual consistency of automatically generated texts in relation to source context is crucial for developing reliable natural language generation applications. Recent literature proposes AlignScore which uses a unified alignment model to evaluate factual consistency and substantially outperforms previous methods across many benchmark tasks. In this paper, we take a closer look of datasets
-
2024In contemporary machine learning approaches to bilingual lexicon induction (BLI), a model learns a mapping between the embedding spaces of a language pair. Recently, the retrieve-and-rank approach to BLI has achieved state-of-the-art results on the task. However, the problem remains challenging in low-resource settings, due to the paucity of data. The task is complicated by factors such as lexical variation
-
2024Large language models (LLMs) tend to inadequately integrate input context during text generation, relying excessively on encoded prior knowledge in model parameters, potentially resulting in generated text with factual inconsistencies or contextually unfaithful content. LLMs utilize two primary knowledge sources: 1) prior (parametric) knowledge from pretraining, and 2) contextual (non-parametric) knowledge
-
2024Dictionary example sentences play an important role in illustrating word definitions and usage, but manually creating quality sentences is challenging. Prior works have demonstrated that language models can be trained to generate example sentences. However, they relied on costly customized models and word sense datasets for generation and evaluation of their work. Rapid advancements in foundational models
-
2024Reinforcement learning from human feedback (RLHF) has been extensively employed to align large language models with user intent. However, proximal policy optimization (PPO) based RLHF is occasionally unstable requiring significant hyperparameter finetuning, and computationally expensive to maximize the estimated reward during alignment. Recently, direct preference optimization (DPO) is proposed to address
Related content
-
May 23, 2023Enforcing a hierarchical clustering of semantically related labels improves performance on rare “long-tail” classification categories. -
May 19, 2023Training on pseudo-labeled data limits the consequences of slight input variations and prevents updated models from backsliding on particular tasks.
-
May 11, 2023Two papers from Amazon Web Services AI present algorithms that alleviate the intensive hyperparameter search and fine-tuning required by privacy-preserving deep learning at very large scales.
-
May 09, 2023Fifth challenge adds new elements and features four new competitors for the $1 million research grant.
-
May 05, 2023Prompt engineering, adaptation of language models, and attempts to remediate large language models’ (LLMs’) “hallucinations” point toward future research in the field.
-
May 03, 2023Generative AI raises new challenges in defining, measuring, and mitigating concerns about fairness, toxicity, and intellectual property, among other things. But work has started on the solutions.
