In retrieval-augmented generation (RAG) question answering systems, generating citations for large language model (LLM) outputs enhances verifiability and helps users identify potential hallucinations. However, we observe two problems in the citations produced by existing attribution methods. First, the citations are typically provided at the sentence or even paragraph level. Long sentences or paragraphs may include a substantial amount of irrelevant content. Second, sentence-level citations may omit information that is essential for verifying the output, forcing users to read the surrounding context. In this paper, we propose generating sub-sentence citations that are both concise and sufficient, thereby reducing the effort required by users to confirm the correctness of the generated output. To this end, we first develop annotation guidelines for such citations and construct a corresponding dataset. Then, we propose an attribution framework for generating citations that adhere to our standards. This framework leverages LLMs to automatically generate fine-tuning data for our task and employs a credit model to filter out low-quality examples. Our experiments on the constructed dataset demonstrate that the propose approach can generate high-quality and more readable citations.

GUWAHATI: Indian Institute of Technology (IIT) Guwahati launched the Samsung Digital Academy Programme by inaugurating the Samsung Digital Academy at the campus. The 14-week long course will be taught through classroom lectures, assignments and lab room sessions, self-study and mini-projects. Extensive tutorials and approach documents will also be provided to students to facilitate practical exercises. The curriculum at the Samsung Innovation Lab at IIT Guwahati will include Internet of Things (IoT), Embedded Systems (ES), Artificial Intelligence (AI) and Machine Learning (ML). The students will be trained on these industry-relevant skills in order to make them job-ready.

GUWAHATI: A Karnataka-born NRI's company will use Artificial Intelligence (AI) to improve the quality of tea and the health of tea workers in tea-rich …