Xinyu: An Efficient LLM-based System for Commentary Generation

• URL: http://arxiv.org/abs/2408.11609v2
• Date: Fri, 23 Aug 2024 03:40:44 GMT
• Title: Xinyu: An Efficient LLM-based System for Commentary Generation
• Authors: Yiquan Wu, Bo Tang, Chenyang Xi, Yu Yu, Pengyu Wang, Yifei Liu, Kun Kuang, Haiying Deng, Zhiyu Li, Feiyu Xiong, Jie Hu, Peng Cheng, Zhonghao Wang, Yi Wang, Yi Luo, Mingchuan Yang,
• Abstract summary: Xinyu is an efficient LLM-based system designed to assist commentators in generating Chinese commentaries. To meet the fundamental requirements, we deconstruct the generation process into sequential steps, proposing targeted strategies and supervised fine-tuning. We observe a significant increase in the efficiency of commentators in real-world scenarios, with the average time spent on creating a commentary dropping from 4 hours to 20 minutes.
• Score: 39.244433599884744
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Commentary provides readers with a deep understanding of events by presenting diverse arguments and evidence. However, creating commentary is a time-consuming task, even for skilled commentators. Large language models (LLMs) have simplified the process of natural language generation, but their direct application in commentary creation still faces challenges due to unique task requirements. These requirements can be categorized into two levels: 1) fundamental requirements, which include creating well-structured and logically consistent narratives, and 2) advanced requirements, which involve generating quality arguments and providing convincing evidence. In this paper, we introduce Xinyu, an efficient LLM-based system designed to assist commentators in generating Chinese commentaries. To meet the fundamental requirements, we deconstruct the generation process into sequential steps, proposing targeted strategies and supervised fine-tuning (SFT) for each step. To address the advanced requirements, we present an argument ranking model for arguments and establish a comprehensive evidence database that includes up-to-date events and classic books, thereby strengthening the substantiation of the evidence with retrieval augmented generation (RAG) technology. To evaluate the generated commentaries more fairly, corresponding to the two-level requirements, we introduce a comprehensive evaluation metric that considers five distinct perspectives in commentary generation. Our experiments confirm the effectiveness of our proposed system. We also observe a significant increase in the efficiency of commentators in real-world scenarios, with the average time spent on creating a commentary dropping from 4 hours to 20 minutes. Importantly, such an increase in efficiency does not compromise the quality of the commentaries.

Related papers

• Benchmarking Large Language Models for Conversational Question Answering in Multi-instructional Documents [61.41316121093604]
  We present InsCoQA, a novel benchmark for evaluating large language models (LLMs) in the context of conversational question answering (CQA) Sourced from extensive, encyclopedia-style instructional content, InsCoQA assesses models on their ability to retrieve, interpret, and accurately summarize procedural guidance from multiple documents. We also propose InsEval, an LLM-assisted evaluator that measures the integrity and accuracy of generated responses and procedural instructions.
  arXiv  Detail & Related papers  (2024-10-01T09:10:00Z)
• Controllable Text Generation for Large Language Models: A Survey [27.110528099257156]
  This paper systematically reviews the latest advancements in Controllable Text Generation for Large Language Models. We categorize CTG tasks into two primary types: content control and control. We address key challenges in current research, including reduced fluency and practicality.
  arXiv  Detail & Related papers  (2024-08-22T17:59:04Z)
• Enhancing Commentary Strategies for Imperfect Information Card Games: A Study of Large Language Models in Guandan Commentary [5.1244906826828736]
  We introduce a novel commentary method that combine Reinforcement Learning (RL) and large language models (LLMs) Our system leverages RL to generate intricate card-playing scenarios and employs LLMs to generate corresponding commentary text. We showcase the substantial enhancement in performance achieved by the proposed commentary framework when applied to open-source LLMs.
  arXiv  Detail & Related papers  (2024-06-23T11:58:26Z)
• Think-then-Act: A Dual-Angle Evaluated Retrieval-Augmented Generation [3.2134014920850364]
  Large language models (LLMs) often face challenges such as temporal misalignment and generating hallucinatory content. We propose a dual-angle evaluated retrieval-augmented generation framework textitThink-then-Act'
  arXiv  Detail & Related papers  (2024-06-18T20:51:34Z)
• Thinking Fair and Slow: On the Efficacy of Structured Prompts for Debiasing Language Models [14.405446719317291]
  Existing debiasing techniques are typically training-based or require access to the model's internals and output distributions. We evaluate a comprehensive end-user-focused iterative framework of debiasing that applies System 2 thinking processes for prompts to induce logical, reflective, and critical text generation.
  arXiv  Detail & Related papers  (2024-05-16T20:27:58Z)
• Generative Judge for Evaluating Alignment [84.09815387884753]
  We propose a generative judge with 13B parameters, Auto-J, designed to address these challenges. Our model is trained on user queries and LLM-generated responses under massive real-world scenarios. Experimentally, Auto-J outperforms a series of strong competitors, including both open-source and closed-source models.
  arXiv  Detail & Related papers  (2023-10-09T07:27:15Z)
• Measuring and Improving Chain-of-Thought Reasoning in Vision-Language Models [61.28463542324576]
  Vision-language models (VLMs) have recently demonstrated strong efficacy as visual assistants that can generate human-like outputs. We evaluate existing state-of-the-art VLMs and find that even the best-performing model is unable to demonstrate strong visual reasoning capabilities and consistency. We propose a two-stage training framework aimed at improving both the reasoning performance and consistency of VLMs.
  arXiv  Detail & Related papers  (2023-09-08T17:49:44Z)
• Large Language Models are Diverse Role-Players for Summarization Evaluation [82.31575622685902]
  A document summary's quality can be assessed by human annotators on various criteria, both objective ones like grammar and correctness, and subjective ones like informativeness, succinctness, and appeal. Most of the automatic evaluation methods like BLUE/ROUGE may be not able to adequately capture the above dimensions. We propose a new evaluation framework based on LLMs, which provides a comprehensive evaluation framework by comparing generated text and reference text from both objective and subjective aspects.
  arXiv  Detail & Related papers  (2023-03-27T10:40:59Z)
• Context-faithful Prompting for Large Language Models [51.194410884263135]
  Large language models (LLMs) encode parametric knowledge about world facts. Their reliance on parametric knowledge may cause them to overlook contextual cues, leading to incorrect predictions in context-sensitive NLP tasks. We assess and enhance LLMs' contextual faithfulness in two aspects: knowledge conflict and prediction with abstention.
  arXiv  Detail & Related papers  (2023-03-20T17:54:58Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.