English
Related papers

Related papers: Echo: Graph-Enhanced Retrieval and Execution Feedb…

200 papers

Retrieval-based conversation systems generally tend to highly rank responses that are semantically similar or even identical to the given conversation context. While the system's goal is to find the most appropriate response, rather than…

Computation and Language · Computer Science 2018-10-09 Denis Fedorenko , Nikita Smetanin , Artem Rodichev

Despite the immense popularity of the Automated Program Repair (APR) field, the question of patch validation is still open. Most of the present-day approaches follow the so-called Generate-and-Validate approach, where first a candidate…

Software Engineering · Computer Science 2021-04-01 Viktor Csuvik , Dániel Horváth , Márk Lajkó , László Vidács

In real-world software engineering tasks, solving a problem often requires understanding and modifying multiple functions, classes, and files across a large codebase. Therefore, on the repository level, it is crucial to extract the relevant…

Software Engineering · Computer Science 2024-09-25 Jicheng Wang , Yifeng He , Hao Chen

AI assistants can increasingly generate and evolve test cases. The challenge is no longer merely to produce them, but also to help engineers understand why a generated artefact exists and what supports it. Existing work has focused on…

Software Engineering · Computer Science 2026-04-27 Eduard Paul Enoiu , Robert Feldt

Progress in hardware model checking depends critically on high-quality benchmarks. However, the community faces a significant benchmark gap: existing suites are limited in number, often distributed only in representations such as BTOR2…

Hardware Architecture · Computer Science 2026-02-27 Guangyu Hu , Xiaofeng Zhou , Wei Zhang , Hongce Zhang

How can AI move beyond imitation toward genuine creativity? This paper proposes the E.A.R.T.H. framework, a five-stage generative pipeline that transforms model-generated errors into creative assets through Error generation, Amplification,…

Artificial Intelligence · Computer Science 2025-08-04 Yusen Peng , Shuhua Mao

Detecting and fixing bugs are two of the most important yet frustrating parts of the software development cycle. Existing bug detection tools are based mainly on static analyzers, which rely on mathematical logic and symbolic reasoning…

Computation and Language · Computer Science 2021-10-04 Dawn Drain , Chen Wu , Alexey Svyatkovskiy , Neel Sundaresan

Retrieval-Augmented Generation (RAG) has become a standard architectural pattern for incorporating domain-specific knowledge into user-facing chat applications powered by Large Language Models (LLMs). RAG systems are characterized by (1) a…

Computation and Language · Computer Science 2025-01-17 Robert Friel , Masha Belyi , Atindriyo Sanyal

Due to the increasing volume, volatility, and diversity of data in virtually all areas of our lives, the ability to detect duplicates in potentially linked data sources is more important than ever before. However, while research is already…

Databases · Computer Science 2024-01-01 Fabian Panse , Wolfram Wingerath , Benjamin Wollmer

Retrieval-augmented generation (RAG) combines document retrieval with large language models to produce responses grounded in external evidence. While several R packages support core components of RAG workflows, integrated evaluation of RAG…

Computation · Statistics 2026-04-28 Muhammad Aimal Rehman , Zhili Lu , Chi-Kuang Yeh

Recent advances in large language models have enabled the development of viable generative retrieval systems. Instead of a traditional document ranking, generative retrieval systems often directly return a grounded generated text as a…

Writing good software tests can be challenging, therefore approaches that support developers are desirable. While generating complete tests automatically is such an approach commonly proposed in research, developers may already have…

Software Engineering · Computer Science 2025-04-30 Severin Primbs , Benedikt Fein , Gordon Fraser

The growing influence of Artificial Intelligence (AI) systems on decision-making in critical domains has exposed their potential to cause significant harms, often rooted in biases embedded across the AI lifecycle. While existing frameworks…

Computers and Society · Computer Science 2025-12-04 Nicoleta Tantalaki , Sophia Vei , Athena Vakali

We introduce a new task named Story Ending Generation (SEG), whic-h aims at generating a coherent story ending from a sequence of story plot. Wepropose a framework consisting of a Generator and a Reward Manager for thistask. The Generator…

Computation and Language · Computer Science 2019-01-14 Yan Zhao , Lu Liu , Chunhua Liu , Ruoyao Yang , Dong Yu

Understanding the reason for emotional support response is crucial for establishing connections between users and emotional support dialogue systems. Previous works mostly focus on generating better responses but ignore interpretability,…

Computation and Language · Computer Science 2024-06-18 Tenggan Zhang , Xinjie Zhang , Jinming Zhao , Li Zhou , Qin Jin

Retrieval-augmented generation (RAG) is increasingly deployed in enterprise search and document-centric assistants, where responses must be grounded in long and complex source materials. In practice, verifying that generated answers…

Computation and Language · Computer Science 2026-03-26 Xunzhuo Liu , Bowei He , Xue Liu , Haichen Zhang , Huamin Chen

The evaluation of Large Language Models (LLMs) for code generation relies heavily on the quality and robustness of test cases. However, existing benchmarks often lack coverage for subtle corner cases, allowing incorrect solutions to pass.…

Software Engineering · Computer Science 2026-02-25 Jingwei Shi , Xinxiang Yin , Jing Huang , Jinman Zhao , Shengyu Tao

Ensuring correctness is crucial for code generation. Formal verification offers a definitive assurance of correctness, but demands substantial human effort in proof construction and hence raises a pressing need for automation. The primary…

Generative AI has shown potential in solving physics problems and providing feedback on assessments. However, results are sometimes still inaccurate, at the wrong level, or using notations and definitions not appropriate for a particular…

Physics Education · Physics 2024-10-28 Gerd Kortemeyer

We present E3, an automated review assistant that augments reviewers and engineering teams by identifying decision-relevant technical concerns in research papers. For each concern, E3 reports its nature, its location, its bearing on the…

Computation and Language · Computer Science 2026-05-27 Yashwardhan Chaudhuri , Sanyam Jain , Paridhi Mundra