相关论文: Vision to Specification: Automating the Transition…

Ensuring that Software Requirements Specifications (SRS) align with higher-level organizational or national requirements is vital, particularly in regulated environments such as finance and aerospace. In these domains, maintaining…

Prevailing alignment methods induce opaque parameter changes, obscuring what models truly learn. To address this, we introduce Feature Steering with Reinforcement Learning (FSRL), a framework that trains a lightweight adapter to steer model…

Requirements expressed in natural language are an indispensable artifact in the software development process, as all stakeholders can understand them. However, their ambiguity poses a persistent challenge. To address this issue,…

Identifying customer needs (CNs) is fundamental to product innovation and marketing strategy. Yet for over thirty years, Voice-of-the-Customer (VOC) applications have relied on professional analysts to manually interpret qualitative data…

Requirements over strings, commonly represented using natural language (NL), are particularly relevant for software systems due to their heavy reliance on string data manipulation. While individual requirements can usually be analyzed…

Model alignment with human preferences is an essential step in making Large Language Models (LLMs) helpful and consistent with human values. It typically consists of supervised fine-tuning (SFT) and reinforcement learning from human…

We present a framework for specifying, training, evaluating, and deploying machine learning models. Our focus is on simplifying cutting edge machine learning for practitioners in order to bring such technologies into production. Recognizing…

A critical stage in the evolving landscape of VLSI design is the design phase that is transformed into register-transfer level (RTL), which specifies system functionality through hardware description languages like Verilog. Generally,…

This paper presents a focused literature survey on the use of large language models (LLM) to assist in writing formal specifications for software. A summary of thirty-five key papers is presented, including examples for specifying programs…

Formal verification of a software system relies on formalising the requirements to which it should adhere, which can be challenging. While formalising requirements from natural-language, we have dependencies that lead to duplication of…

While reinforcement learning (RL) has proven highly effective for general reasoning in vision-language models, its application to tasks requiring deep understanding of information-rich images and structured output generation remains…

Feature attribution is often loosely presented as the process of selecting a subset of relevant features as a rationale of a prediction. Task-dependent by nature, precise definitions of "relevance" encountered in the literature are however…

Automatic code generation has been a longstanding research topic. With the advancement of general-purpose large language models (LLMs), the ability to code stands out as one important measure to the model's reasoning performance. Usually, a…

Slot filling is a crucial component in task-oriented dialog systems that is used to parse (user) utterances into semantic concepts called slots. An ontology is defined by the collection of slots and the values that each slot can take. The…

Vision-based reinforcement learning (RL) is a promising technique to solve control tasks involving images as the main observation. State-of-the-art RL algorithms still struggle in terms of sample efficiency, especially when using image…

Continuous sign language recognition (SLR) aims to translate a signing sequence into a sentence. It is very challenging as sign language is rich in vocabulary, while many among them contain similar gestures and motions. Moreover, it is…

Requirements elicitation, a critical, yet time-consuming and challenging step in product development, often fails to capture the full spectrum of user needs. This may lead to products that fall short of expectations. This paper introduces a…

Low-Rank Adaptation (LoRA) has become a cornerstone of parameter-efficient fine-tuning (PEFT). Yet, its efficacy is hampered by two fundamental limitations: semantic drift, by treating all update directions with equal importance, and…

Previous LLMs-based RL studies typically follow either supervised learning with high annotation costs, or unsupervised paradigms using voting or entropy-based rewards. However, their performance remains far from satisfactory due to the…

Signal Temporal Logic (STL) is a formal language for specifying real-time behaviors of cyber-physical systems (CPS). Automatically transforming natural language requirements into STL specifications has received growing attention. Recent…