Pith. sign in

REVIEW 5 cited by

CodeIE: Large Code Generation Models are Better Few-Shot Information Extractors

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 2305.05711 v2 pith:ACMTAOMU submitted 2023-05-09 cs.CL cs.AI

Peng Li , Tianxiang Sun , Qiong Tang , Hang Yan , Yuanbin Wu , Xuanjing Huang , Xipeng Qiu This is my paper · ORCID
classification cs.CLcs.AI
keywords taskscodenl-llmscode-llmsfew-shotlanguagellmsmodels
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Large language models (LLMs) pre-trained on massive corpora have demonstrated impressive few-shot learning ability on many NLP tasks. A common practice is to recast the task into a text-to-text format such that generative LLMs of natural language (NL-LLMs) like GPT-3 can be prompted to solve it. However, it is nontrivial to perform information extraction (IE) tasks with NL-LLMs since the output of the IE task is usually structured and therefore is hard to be converted into plain text. In this paper, we propose to recast the structured output in the form of code instead of natural language and utilize generative LLMs of code (Code-LLMs) such as Codex to perform IE tasks, in particular, named entity recognition and relation extraction. In contrast to NL-LLMs, we show that Code-LLMs can be well-aligned with these IE tasks by designing code-style prompts and formulating these IE tasks as code generation tasks. Experiment results on seven benchmarks show that our method consistently outperforms fine-tuning moderate-size pre-trained models specially designed for IE tasks (e.g., UIE) and prompting NL-LLMs under few-shot settings. We further conduct a series of in-depth analyses to demonstrate the merits of leveraging Code-LLMs for IE tasks.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 5 Pith papers

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

  1. GuideX: Guided Synthetic Data Generation for Zero-Shot Information Extraction

    cs.CL 2025-05 conditional novelty 6.0 of 10

    A fully automated pipeline for generating annotation schemas, guidelines, and synthetic labeled examples from documents improves zero-shot NER after fine-tuning.

  2. MPL: Multiple Programming Languages with Large Language Models for Information Extraction

    cs.CL 2025-05 conditional novelty 6.0 of 10

    Using multiple programming languages as code-style prompts during fine-tuning improves LLM information extraction accuracy over single-language prompting.

  3. A Semantic Parsing Framework for End-to-End Time Normalization

    cs.CL 2025-07 conditional novelty 5.0 of 10

    Time normalization can be treated as executable SCATE Python code generation, and a 0.5B model fine-tuned on LLM-augmented data beats zero-shot LLM prompting on TempEval-2013.

  4. 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.

  5. RetrieveAll: A Multilingual Named Entity Recognition Framework with Large Language Models

    cs.CL 2025-05 conditional novelty 5.0 of 10

    RetrieveAll combines per-language LoRA adapters with retrieval of entity and context examples to improve multilingual NER, claiming an average 12.1% F1 gain on PAN-X.

Pith tools