# WebCPM: Interactive Web Search for Chinese Long-form Question Answering

arXiv: https://arxiv.org/abs/2305.06849 · HTML: https://mlsanity.com/paper/2305.06849/

## Key facts

- Cited by 93 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 38 references that are in the map.
- First posted on arXiv 11 May 2023.

## Builds on (most cited first, 25 of 25)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [Scaling Laws for Neural Language Models](https://mlsanity.com/paper/2001.08361/) (2020)
- [BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension](https://mlsanity.com/paper/1910.13461/) (2019)
- [Learning to summarize from human feedback](https://mlsanity.com/paper/2009.01325/) (2020)
- [Do As I Can, Not As I Say: Grounding Language in Robotic Affordances](https://mlsanity.com/paper/2204.01691/) (2022)
- [mT5: A massively multilingual pre-trained text-to-text transformer](https://mlsanity.com/paper/2010.11934/) (2020)
- [WebGPT: Browser-assisted question-answering with human feedback](https://mlsanity.com/paper/2112.09332/) (2021)
- [WebShop: Towards Scalable Real-World Web Interaction with Grounded Language Agents](https://mlsanity.com/paper/2207.01206/) (2022)
- [LaMDA: Language Models for Dialog Applications](https://mlsanity.com/paper/2201.08239/) (2022)
- [Inner Monologue: Embodied Reasoning through Planning with Language Models](https://mlsanity.com/paper/2207.05608/) (2022)
- [Multilingual Denoising Pre-training for Neural Machine Translation](https://mlsanity.com/paper/2001.08210/) (2020)
- [Language Models as Zero-Shot Planners: Extracting Actionable Knowledge for Embodied Agents](https://mlsanity.com/paper/2201.07207/) (2022)
- [ELI5: Long Form Question Answering](https://mlsanity.com/paper/1907.09190/) (2019)
- [Neural Text Generation with Unlikelihood Training](https://mlsanity.com/paper/1908.04319/) (2019)
- [Teaching language models to support answers with verified quotes](https://mlsanity.com/paper/2203.11147/) (2022)
- [Hurdles to Progress in Long-form Question Answering](https://mlsanity.com/paper/2103.06332/) (2021)
- [DuReader: a Chinese Machine Reading Comprehension Dataset from Real-world Applications](https://mlsanity.com/paper/1711.05073/) (2017)
- [A Span-Extraction Dataset for Chinese Machine Reading Comprehension](https://mlsanity.com/paper/1810.07366/) (2018)
- [Investigating Prior Knowledge for Challenging Chinese Machine Reading Comprehension](https://mlsanity.com/paper/1904.09679/) (2019)
- [CPT: A Pre-Trained Unbalanced Transformer for Both Chinese Language Understanding and Generation](https://mlsanity.com/paper/2109.05729/) (2021)
- [CPM: A Large-scale Generative Chinese Pre-trained Language Model](https://mlsanity.com/paper/2012.00413/) (2020)
- [Mengzi: Towards Lightweight yet Ingenious Pre-trained Models for Chinese](https://mlsanity.com/paper/2110.06696/) (2021)
- [How Do We Answer Complex Questions: Discourse Structure of Long-form Answers](https://mlsanity.com/paper/2203.11048/) (2022)
- [Modeling Exemplification in Long-form Question Answering via Retrieval](https://mlsanity.com/paper/2205.09278/) (2022)

## Built on by (most cited first, 30 of 93)

- [ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs](https://mlsanity.com/paper/2307.16789/) (2023)
- [A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions](https://mlsanity.com/paper/2311.05232/) (2023)
- [Large Language Models for Information Retrieval: A Survey](https://mlsanity.com/paper/2308.07107/) (2023)
- [A Survey on Knowledge Distillation of Large Language Models](https://mlsanity.com/paper/2402.13116/) (2024)
- [Tool Learning with Large Language Models: A Survey](https://mlsanity.com/paper/2405.17935/) (2024)
- [Survey on Factuality in Large Language Models: Knowledge, Retrieval and Domain-Specificity](https://mlsanity.com/paper/2310.07521/) (2023)
- [Large Language Model Agent: A Survey on Methodology, Applications and Challenges](https://mlsanity.com/paper/2503.21460/) (2025)
- [StableToolBench: Towards Stable Large-Scale Benchmarking on Tool Learning of Large Language Models](https://mlsanity.com/paper/2403.07714/) (2024)
- [GUICourse: From General Vision Language Models to Versatile GUI Agents](https://mlsanity.com/paper/2406.11317/) (2024)
- [MatPlotAgent: Method and Evaluation for LLM-Based Agentic Scientific Data Visualization](https://mlsanity.com/paper/2402.11453/) (2024)
- [From Matching to Generation: A Survey on Generative Information Retrieval](https://mlsanity.com/paper/2404.14851/) (2024)
- [Proactive Agent: Shifting LLM Agents from Reactive Responses to Active Assistance](https://mlsanity.com/paper/2410.12361/) (2024)
- [GTA: A Benchmark for General Tool Agents](https://mlsanity.com/paper/2407.08713/) (2024)
- [AvaTaR: Optimizing LLM Agents for Tool Usage via Contrastive Reasoning](https://mlsanity.com/paper/2406.11200/) (2024)
- [A Survey of Large Language Models Attribution](https://mlsanity.com/paper/2311.03731/) (2023)
- [Confucius: Iterative Tool Learning from Introspection Feedback by Easy-to-Difficult Curriculum](https://mlsanity.com/paper/2308.14034/) (2023)
- [Training Large Language Models for Reasoning through Reverse Curriculum Reinforcement Learning](https://mlsanity.com/paper/2402.05808/) (2024)
- [LLM With Tools: A Survey](https://mlsanity.com/paper/2409.18807/) (2024)
- [OdysseyBench: Evaluating LLM Agents on Long-Horizon Complex Office Application Workflows](https://mlsanity.com/paper/2508.09124/) (2025)
- [Tool Learning in the Wild: Empowering Language Models as Automatic Tool Agents](https://mlsanity.com/paper/2405.16533/) (2024)
- [TPTU: Large Language Model-based AI Agents for Task Planning and Tool Usage](https://mlsanity.com/paper/2308.03427/) (2023)
- [Instruction-tuned Language Models are Better Knowledge Learners](https://mlsanity.com/paper/2402.12847/) (2024)
- [Learning to Use Tools via Cooperative and Interactive Agents](https://mlsanity.com/paper/2403.03031/) (2024)
- [FinTextQA: A Dataset for Long-form Financial Question Answering](https://mlsanity.com/paper/2405.09980/) (2024)
- [LLatrieval: LLM-Verified Retrieval for Verifiable Generation](https://mlsanity.com/paper/2311.07838/) (2023)
- [Generate-then-Ground in Retrieval-Augmented Generation for Multi-hop Question Answering](https://mlsanity.com/paper/2406.14891/) (2024)
- [From Exploration to Mastery: Enabling LLMs to Master Tools via Self-Driven Interactions](https://mlsanity.com/paper/2410.08197/) (2024)
- [Retrieve, Summarize, Plan: Advancing Multi-hop Question Answering with an Iterative Approach](https://mlsanity.com/paper/2407.13101/) (2024)
- [Reducing Tool Hallucination via Reliability Alignment](https://mlsanity.com/paper/2412.04141/) (2024)
- [A Survey on Knowledge-Oriented Retrieval-Augmented Generation](https://mlsanity.com/paper/2503.10677/) (2025)

## Abstract (arXiv)

Long-form question answering (LFQA) aims at answering complex, open-ended questions with detailed, paragraph-length responses. The de facto paradigm of LFQA necessitates two procedures: information retrieval, which searches for relevant supporting facts, and information synthesis, which integrates these facts into a coherent answer. In this paper, we introduce WebCPM, the first Chinese LFQA dataset. One unique feature of WebCPM is that its information retrieval is based on interactive web search, which engages with a search engine in real time. Following WebGPT, we develop a web search interface. We recruit annotators to search for relevant information using our interface and then answer questions. Meanwhile, the web search behaviors of our annotators would be recorded. In total, we collect 5,500 high-quality question-answer pairs, together with 14,315 supporting facts and 121,330 web search actions. We fine-tune pre-trained language models to imitate human behaviors for web search and to generate answers based on the collected facts. Our LFQA pipeline, built on these fine-tuned models, generates answers that are no worse than human-written ones in 32.5% and 47.5% of the cases on our dataset and DuReader, respectively.