Pith. sign in

REVIEW 6 cited by

YAYI-UIE: A Chat-Enhanced Instruction Tuning Framework for Universal Information Extraction

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2312.15548 v3 pith:YDC7UO7N submitted 2023-12-24 cs.CL cs.AI

Xinglin Xiao , Yijie Wang , Nan Xu , Yuqi Wang , Hanxuan Yang , Minzheng Wang , Yin Luo , Lei Wang
show 2 more authors
Wenji Mao Daniel Zeng
This is my paper · ORCID
classification cs.CLcs.AI
keywords extractioninformationchinesedataenglishframeworkperformancechat-enhanced
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

The difficulty of the information extraction task lies in dealing with the task-specific label schemas and heterogeneous data structures. Recent work has proposed methods based on large language models to uniformly model different information extraction tasks. However, these existing methods are deficient in their information extraction capabilities for Chinese languages other than English. In this paper, we propose an end-to-end chat-enhanced instruction tuning framework for universal information extraction (YAYI-UIE), which supports both Chinese and English. Specifically, we utilize dialogue data and information extraction data to enhance the information extraction performance jointly. Experimental results show that our proposed framework achieves state-of-the-art performance on Chinese datasets while also achieving comparable performance on English datasets under both supervised settings and zero-shot settings.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 6 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Improving Natural Language Understanding for LLMs via Large-Scale Instruction Synthesis

    cs.CL 2025-02 conditional novelty 6.0 of 10

    A large synthetic instruction corpus with guidelines, preference rules, and format variants improves LLM performance on five NLU benchmarks by an average of 3.1%.

  2. MR-UIE: Multi-Perspective Reasoning with Reinforcement Learning for Universal Information Extraction

    cs.CL 2025-09 conditional novelty 5.0 of 10

    A pipeline that combines multi-perspective chain-of-thought reasoning with reinforcement learning for universal information extraction, showing modest gains that are overstated in the text.

  3. KnowCoder-V2: Deep Knowledge Analysis

    cs.AI 2025-06 conditional novelty 5.0 of 10

    KnowCoder-V2 augments deep research with offline knowledge organization and code-based knowledge computation, reporting gains on information extraction, KBQA, and LLM-judged report generation.

  4. Schema as Parameterized Tools for Universal Information Extraction

    cs.CL 2025-06 conditional novelty 5.0 of 10

    SPT turns predefined IE schemas into trainable token embeddings, enabling one small model to handle closed, open, and on-demand extraction through schema retrieval, generation, and infilling.

  5. MAQInstruct: Instruction-based Unified Event Relation Extraction

    cs.CL 2025-02 conditional novelty 5.0 of 10

    MAQInstruct reformulates event relation extraction as relation-specific multiple-answer QA with a bipartite matching loss, reducing inference samples from n^2 to k*n and improving F1 across three LLMs on four datasets.

  6. PlanE: Meta Planning of Data, Tuning, and Inference for Extractive-based LLMs

    cs.AI 2026-05 conditional novelty 4.0 of 10

    A quadratic meta-planner trained on a few model-dataset runs selects the optimal data-tuning-inference configuration for extractive LLMs, matching grid search on three IE tasks.

Pith tools