相关论文: AFSCR: Annotation of Functional Satisfaction Condi…

Data scarcity has been the main factor that hinders the progress of event extraction. To overcome this issue, we propose a Self-Training with Feedback (STF) framework that leverages the large-scale unlabeled data and acquires feedback for…

Analysis tools like abstract interpreters, symbolic execution tools and testing tools usually require a proper context to give useful results when analyzing a particular function. Such a context initializes the function parameters and…

Despite the critical need to align search targets with users' intention, retrievers often only prioritize query information without delving into the users' intended search context. Enhancing the capability of retrievers to understand…

Multi-objective preference alignment in language models often encounters a challenging trade-off: optimizing for one human preference (e.g., helpfulness) frequently compromises others (e.g., harmlessness) due to the inherent conflicts…

This paper presents a new framework for constructing congruence closure of a finite set of ground equations over uninterpreted symbols and interpreted symbols for the group axioms. In this framework, ground equations are flattened into…

This paper presents a novel optimization framework for automatic speech recognition (ASR) with the aim of reducing hallucinations produced by an ASR model. The proposed framework optimizes the ASR model to maximize an expected factual…

An automated metric to evaluate dialogue quality is vital for optimizing data driven dialogue management. The common approach of relying on explicit user feedback during a conversation is intrusive and sparse. Current models to estimate…

We introduce \textsc{CAT}, a framework designed to evaluate and visualize the \emph{interplay} of \emph{accuracy} and \emph{response consistency} of Large Language Models (LLMs) under controllable input variations, using multiple-choice…

General Alignment has improved average-case helpfulness and safety, but current alignment practice still rewards confident, single-turn responses. The problem is not only that models fail on edge cases; it is that current evaluation makes…

Goal models have been widely used in Computer Science to represent software requirements, business objectives, and design qualities. Existing goal modelling techniques, however, have shown limitations of expressiveness and/or tractability…

Decision support system in Requirements engineering plays an important role in software development life cycle. The relationship between functional and non-functional requirements often plays a crucial role in resolving conflicts or…

We present Assume-Guarantee-Repair (AGR) - a novel framework which verifies that a program satisfies a set of properties and also repairs the program in case the verification fails. We consider communicating programs - these are simple…

The lack of labeled data is a major obstacle to learning high-quality sentence embeddings. Recently, self-supervised contrastive learning (SCL) is regarded as a promising way to address this problem. However, the existing works mainly rely…

Code completion is widely used by software developers to provide coding suggestions given a partially written code snippet. Apart from the traditional code completion methods, which only support single token completion at minimal positions,…

Detecting and handling misspecified objectives, such as reward functions, has been widely recognized as one of the central challenges within the domain of Artificial Intelligence (AI) safety research. However, even with the recognition of…

Aligning the activities of an organization with its business goals is a challenging task that is critical for success. Alignment in a multi-organizational setting requires the integration of different internal or external organizational…

Before deploying outputs from foundation models in high-stakes tasks, it is imperative to ensure that they align with human values. For instance, in radiology report generation, reports generated by a vision-language model must align with…

Language model alignment is a critical step in training modern generative language models. Alignment targets to improve win rate of a sample from the aligned model against the base model. Today, we are increasingly using inference-time…

The quality assessment of Artificial Intelligence (AI) systems is a fundamental challenge due to their inherently probabilistic nature. Standards such as ISO/IEC 25059 provide a quality model, but they lack practical and statistically…

In this paper, we propose FFCI, a framework for fine-grained summarization evaluation that comprises four elements: faithfulness (degree of factual consistency with the source), focus (precision of summary content relative to the…