We employ a characterization of linguistic complexity from psycholinguistic and language acquisition research to develop data-driven curricula to understand the underlying linguistic knowledge that models learn to add...
详细信息
ISBN:
(纸本)9798891760608
We employ a characterization of linguistic complexity from psycholinguistic and language acquisition research to develop data-driven curricula to understand the underlying linguistic knowledge that models learn to address NLP tasks. The novelty of our approach is in the development of linguistic curricula derived from data, existing knowledge about linguistic complexity, and model behavior during training. By analyzing several benchmark NLP datasets, our curriculum learning approaches identify sets of linguistic metrics (indices) that inform the challenges and reasoning required to address each task. Our work will inform future research in all NLP areas, allowing linguistic complexity to be considered early in the research and development process. In addition, our work prompts an examination of gold standards and fair evaluation in NLP.
Retrieval-augmented generation (RAG) techniques have proven to be effective in integrating up-to-date information, mitigating hallucinations, and enhancing response quality, particularly in specialized domains. While ...
详细信息
In the age of neural naturallanguageprocessing, there are plenty of works trying to derive interpretations of neural models. Intuitively, when gold rationales exist during training, one can additionally train the mo...
详细信息
ISBN:
(纸本)9798891760608
In the age of neural naturallanguageprocessing, there are plenty of works trying to derive interpretations of neural models. Intuitively, when gold rationales exist during training, one can additionally train the model to match its interpretation with the rationales. However, this intuitive idea has not been fully explored. In this paper, we propose a framework of utilizing interpretation methods and gold rationales to enhance models. Our framework is very general in the sense that it can incorporate various interpretation methods. Previously proposed gradient-based methods can be shown as an instance of our framework. We also propose two novel instances utilizing two other types of interpretation methods, erasure/replace-based and extractor-based methods, for model enhancement. We conduct comprehensive experiments on a variety of tasks. Experimental results show that our framework is effective especially in low-resource settings in enhancing models with various interpretation methods, and our two newly-proposed methods outperform gradient-based methods in most settings. Code is available at https://***/Chord-Chen-30/UIMER.
In-context learning (ICL) is a few-shot learning paradigm that involves learning mappings through input-output pairs and appropriately applying them to new instances. Despite the remarkable ICL capabilities demonstrat...
详细信息
naturallanguage explanations represent a proxy for evaluating explanation-based and multi-step naturallanguage Inference (NLI) models. However, assessing the validity of explanations for NLI is challenging as it typ...
详细信息
language model alignment research often attempts to ensure that models are not only helpful and harmless, but also truthful and unbiased. However, optimizing these objectives simultaneously can obscure how improving o...
While large visual-language models (LVLM) have shown promising results on traditional visual question answering benchmarks, it is still challenging for them to answer complex VQA problems which requires diverse world ...
详细信息
Research on sound design evaluation methodologies relating to connotation, or the evocation of mental imagery is limited. Prior tools for data analysis have fallen short, making the process time-consuming and difficul...
详细信息
ISBN:
(纸本)9798400708183
Research on sound design evaluation methodologies relating to connotation, or the evocation of mental imagery is limited. Prior tools for data analysis have fallen short, making the process time-consuming and difficult: We explore here a variety of new AI-powered naturallanguageprocessing tools to evaluate the data. Results showed that free verbalization is a fruitful method to answer some research questions about sound, giving rise to many interesting insights and leading to further research questions.
Building socially-intelligent AI agents (Social-AI) is a multidisciplinary, multimodal research goal that involves creating agents that can sense, perceive, reason about, learn from, and respond to affect, behavior, a...
详细信息
Social scientists use surveys to probe the opinions and beliefs of populations, but these methods are slow, costly, and prone to biases. Recent advances in large language models (LLMs) enable the creation of computati...
详细信息
暂无评论