# FactGuard: Leveraging Multi-Agent Systems to Generate Answerable and Unanswerable Questions for Enhanced Long-Context LLM Extraction

arXiv: https://arxiv.org/abs/2504.05607 · HTML: https://mlsanity.com/paper/2504.05607/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in General LLM agent frameworks and benchmarks, one of 16 directions in LLM agents and tool use.
- Builds on 30 of its 53 references that are in the map.
- First posted on arXiv 8 Apr 2025.

## Placed in

- LLM agents and tool use / [General LLM agent frameworks and benchmarks](https://mlsanity.com/agents/general-llm-agent-frameworks-and-benchmarks/)

## Builds on (most cited first, 30 of 30)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Qwen2.5 Technical Report](https://mlsanity.com/paper/2412.15115/) (2024)
- [RoFormer: Enhanced Transformer with Rotary Position Embedding](https://mlsanity.com/paper/2104.09864/) (2021)
- [SQuAD: 100,000+ Questions for Machine Comprehension of Text](https://mlsanity.com/paper/1606.05250/) (2016)
- [Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2204.05862/) (2022)
- [Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context](https://mlsanity.com/paper/2403.05530/) (2024)
- [Learning to summarize from human feedback](https://mlsanity.com/paper/2009.01325/) (2020)
- [MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework](https://mlsanity.com/paper/2308.00352/) (2023)
- [Know What You Don't Know: Unanswerable Questions for SQuAD](https://mlsanity.com/paper/1806.03822/) (2018)
- [LongBench: A Bilingual, Multitask Benchmark for Long Context Understanding](https://mlsanity.com/paper/2308.14508/) (2023)
- [DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model](https://mlsanity.com/paper/2405.04434/) (2024)
- [Train Short, Test Long: Attention with Linear Biases Enables Input Length Extrapolation](https://mlsanity.com/paper/2108.12409/) (2021)
- [Teaching Machines to Read and Comprehend](https://mlsanity.com/paper/1506.03340/) (2015)
- [ChatEval: Towards Better LLM-based Evaluators through Multi-Agent Debate](https://mlsanity.com/paper/2308.07201/) (2023)
- [LooGLE: Can Long-Context Language Models Understand Long Contexts?](https://mlsanity.com/paper/2311.04939/) (2023)
- [Agents: An Open-source Framework for Autonomous Language Agents](https://mlsanity.com/paper/2309.07870/) (2023)
- [AgentInstruct: Toward Generative Teaching with Agentic Flows](https://mlsanity.com/paper/2407.03502/) (2024)
- [KERPLE: Kernelized Relative Positional Embedding for Length Extrapolation](https://mlsanity.com/paper/2205.09921/) (2022)
- [Igniting Language Intelligence: The Hitchhiker's Guide From Chain-of-Thought Reasoning to Language Agents](https://mlsanity.com/paper/2311.11797/) (2023)
- [Retrieval Augmented Generation (RAG) and Beyond: A Comprehensive Survey on How to Make your LLMs use External Data More Wisely](https://mlsanity.com/paper/2409.14924/) (2024)
- [(QA)2: Question Answering with Questionable Assumptions](https://mlsanity.com/paper/2212.10003/) (2022)
- [Relation Extraction : A Survey](https://mlsanity.com/paper/1712.05191/) (2017)
- [A Survey on Machine Reading Comprehension Systems](https://mlsanity.com/paper/2001.01582/) (2020)
- [Read + Verify: Machine Reading Comprehension with Unanswerable Questions](https://mlsanity.com/paper/1808.05759/) (2018)
- [Don't Just Say "I don't know"! Self-aligning Large Language Models for Responding to Unknown Questions with Explanations](https://mlsanity.com/paper/2402.15062/) (2024)
- [TigerBot: An Open Multilingual Multitask LLM](https://mlsanity.com/paper/2312.08688/) (2023)
- [Efficient Pretraining Data Selection for Language Models via Multi-Actor Collaboration](https://mlsanity.com/paper/2410.08102/) (2024)
- [SCENE: Self-Labeled Counterfactuals for Extrapolating to Negative Examples](https://mlsanity.com/paper/2305.07984/) (2023)
- [RetinaQA: A Robust Knowledge Base Question Answering Model for both Answerable and Unanswerable Questions](https://mlsanity.com/paper/2403.10849/) (2024)

## Built on by (most cited first, 1 of 1)

- [Hallucinations Undermine Trust; Metacognition is a Way Forward](https://mlsanity.com/paper/2605.01428/) (2026)

## Abstract (arXiv)

Despite the success of Large Language Models (LLMs) in long-context tasks, their reliability in recognizing unanswerable questions remains a critical challenge. In information-seeking scenarios, models often suffer from overconfidence and hallucinations when evidence is missing or misleading. In this paper, we propose FACTGUARD, a systematic multi-task workflow for generating evidence-grounded answerable and unanswerable questions. We introduce FACTGUARD-BENCH, a benchmark comprising 25,220 examples with context lengths up to 128K, specifically targeting Lack of Evidence and Misleading Evidence scenarios. Evaluations of eleven representative open-source and proprietary LLMs reveal a significant reliability gap: models struggle to reject unanswerable questions as context scales, with the leading model achieving only 71.62% accuracy. By training with FACTGUARD-BENCH, we improve overall accuracy to 81.17% and significantly enhance models' reasoned rejection capabilities. Our work provides a scalable path toward building more faithful and trustworthy long-context LLMs. Our source is publicly available at https://github.com/biaoliu-kiritsugu/FactGuard.