相关论文: Language Generation with Strictly Proper Scoring R…

Reinforcement learning (RL) can align language models with non-differentiable reward signals, such as human preferences. However, a major challenge arises from the sparsity of these reward signals - typically, there is only a single reward…

Image scoring is a crucial task in numerous real-world applications. To trust a model's judgment, understanding its rationale is essential. This paper proposes a novel training method for Vision Language Models (VLMs) to generate not only…

Trustworthiness of generative language models (GLMs) is crucial in their deployment to critical decision making systems. Hence, certified risk control methods such as selective prediction and conformal prediction have been applied to…

Evaluating the quality of generated text automatically remains a significant challenge. Conventional reference-based metrics have been shown to exhibit relatively weak correlation with human evaluations. Recent research advocates the use of…

Mathematical optimization is a powerful tool for structured decision-making across domains such as resource allocation and planning. Formulating optimization models faithful to reality, though, remains a significant bottleneck as it…

As machine learning models continue to swiftly advance, calibrating their performance has become a major concern prior to practical and widespread implementation. Most existing calibration methods often negatively impact model accuracy due…

Code-mixing, the practice of alternating between two or more languages in an utterance, is a common phenomenon in multilingual communities. Due to the colloquial nature of code-mixing, there is no singular correct way to translate an…

Building accurate language models that capture meaningful long-term dependencies is a core challenge in natural language processing. Towards this end, we present a calibration-based approach to measure long-term discrepancies between a…

Reward modeling is crucial for aligning large language models (LLMs) with human preferences, especially in reinforcement learning from human feedback (RLHF). However, current reward models mainly produce scalar scores and struggle to…

Score-based generative models (SGMs) are a popular family of deep generative models that achieve leading image generation quality. Early studies extend SGMs to tackle class-conditional generation by coupling an unconditional SGM with the…

Large language models (LLMs) hold promise for generating plans for complex tasks, but their effectiveness is limited by sequential execution, lack of control flow models, and difficulties in skill retrieval. Addressing these issues is…

Proper scoring rules have been a subject of growing interest in recent years, not only as tools for evaluation of probabilistic forecasts but also as methods for estimating probability distributions. In this article, we review the…

This article introduces semantically meaningful causal language modeling (SMCLM), a selfsupervised method of training autoregressive models to generate semantically equivalent text. Our approach involves using semantically meaningful text…

Writing code requires significant time and effort in software development. To automate this process, researchers have made substantial progress using Large Language Models (LLMs) for code generation. Many benchmarks like HumanEval and…

The rise of Large Language Models (LLMs) in software engineering, particularly in code generation, has garnered significant attention. However, assessing the quality of AI-generated code remains a challenge due to the inherent complexity of…

Numerical reasoning is vital for natural language processing models to understand and process numerical information in real-world scenarios. Most current methods first generate the Intermediate Meaning Representations (IMRs) of questions…

Large Language Models (LLMs) are increasingly used to generate synthetic textual data for training smaller specialized models. However, a comparison of various generation strategies for low-resource language settings is lacking. While…

Language Models (LMs) are increasingly being used for code generation, but ensuring the correctness of generated programs remains a significant challenge. Although imperfect code may be acceptable during software development with human…

With the rapid development of large language models (LLMs), the applications of LLMs have grown substantially. In the education domain, LLMs demonstrate significant potential, particularly in automatic text generation, which enables the…

Large Language Models (LLMs) are nowadays extensively used for various types of software engineering tasks, primarily code generation. Previous research has shown how suitable prompt engineering could help developers in improving their code…