Extensive efforts have been made before the public release of Large language models (LLMs) to align their behaviors with human values. However, even meticulously aligned LLMs remain vulnerable to malicious manipulatio...
详细信息
Mitigating explicit and implicit biases in Large language Models (LLMs) has become a critical focus in the field of naturallanguageprocessing. However, many current methodologies evaluate scenarios in isolation, wit...
详细信息
Multimodal large language models (MLLMs) have attracted increasing attention in the past few years, but they may still generate descriptions that include objects not present in the corresponding images, a phenomenon k...
详细信息
There is a growing interest in expanding the input capacity of language models (LMs) across various domains. However, simply increasing the context window does not guarantee robust performance across diverse long-inpu...
详细信息
As one of the common rhetorical devices, puns play a vital role in linguistic study, including the comprehensive analysis of linguistic humor. Although large language models (LLMs) have been widely explored on various...
详细信息
Recently, post-processing networks (PPNs), which modify the outputs of arbitrary modules including non-differentiable ones in task-oriented dialogue systems, have been proposed. PPNs have successfully improved the dia...
详细信息
ISBN:
(纸本)9798891760608
Recently, post-processing networks (PPNs), which modify the outputs of arbitrary modules including non-differentiable ones in task-oriented dialogue systems, have been proposed. PPNs have successfully improved the dialogue performance by post-processingnaturallanguage understanding (NLU), dialogue state tracking (DST), and dialogue policy (Policy) modules with a classification-based approach. However, they cannot be applied to naturallanguage generation (NLG) modules because the post-processing of utterances output by NLG modules requires a generative approach. In this study, we propose a new post-processing component for NLG, generative post-processing networks (GenPPNs). For optimizing GenPPNs via reinforcement learning, the reward function incorporates dialogue act contribution, a new measure to evaluate the contribution of GenPPN-generated utterances with regard to task completion in dialogue. Through simulation and human evaluation experiments based on the MultiWOZ dataset, we confirmed that GenPPNs improve the task completion performance of task-oriented dialogue systems(1).
Improving the effectiveness and efficiency of large language models (LLMs) simultaneously is a critical yet challenging research goal. In this paper, we find that low-rank pre-training, normally considered as efficien...
详细信息
Recent advancements in large language Models (LMs) have significantly enhanced their capabilities across various domains, including naturallanguage understanding and generation. In this paper, we investigate the appl...
详细信息
Machine learning (ML) systems in naturallanguageprocessing (NLP) face significant challenges in generalizing to out-of-distribution (OOD) data, where the test distribution differs from the training data distribution...
详细信息
ISBN:
(纸本)9798891760608
Machine learning (ML) systems in naturallanguageprocessing (NLP) face significant challenges in generalizing to out-of-distribution (OOD) data, where the test distribution differs from the training data distribution. This poses important questions about the robustness of NLP models and their high accuracy, which may be artificially inflated due to their underlying sensitivity to systematic biases. Despite these challenges, there is a lack of comprehensive surveys on the generalization challenge from an OOD perspective in naturallanguage understanding. Therefore, this paper aims to fill this gap by presenting the first comprehensive review of recent progress, methods, and evaluations on this topic. We further discuss the challenges involved and potential future research directions. By providing convenient access to existing work, we hope this survey will encourage future research in this area.
The proceedings contain 10 papers. The topics discussed include: failure transducers and applications in knowledge-based text processing;transliterated mobile keyboard input via weighted finite-state transducers;harmo...
The proceedings contain 10 papers. The topics discussed include: failure transducers and applications in knowledge-based text processing;transliterated mobile keyboard input via weighted finite-state transducers;harmonic serialism and finite-state optimality theory;bounded-depth high-coverage search space for noncrossing parses;multi-tape computing with synchronous relations;finite-state morphological analysis for Marathi;word transduction for addressing the OOV problem in machine translation for similar resource-scarce languages;a FST description of noun and verb morphology of Azarbaijani Turkish;and evaluation of finite state morphological analyzers based on paradigm extraction from wiktionary.
暂无评论