# Expect the Unexpected: FailSafe Long Context QA for Finance

arXiv: https://arxiv.org/abs/2502.06329 · HTML: https://mlsanity.com/paper/2502.06329/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 45 references that are in the map.
- First posted on arXiv 10 Feb 2025.

## Builds on (most cited first, 17 of 17)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Lost in the Middle: How Language Models Use Long Contexts](https://mlsanity.com/paper/2307.03172/) (2023)
- [Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context](https://mlsanity.com/paper/2403.05530/) (2024)
- [RULER: What's the Real Context Size of Your Long-Context Language Models?](https://mlsanity.com/paper/2404.06654/) (2024)
- [Fantastically Ordered Prompts and Where to Find Them: Overcoming Few-Shot Prompt Order Sensitivity](https://mlsanity.com/paper/2104.08786/) (2021)
- [Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting](https://mlsanity.com/paper/2310.11324/) (2023)
- [FinanceBench: A New Benchmark for Financial Question Answering](https://mlsanity.com/paper/2311.11944/) (2023)
- [FinBen: A Holistic Financial Benchmark for Large Language Models](https://mlsanity.com/paper/2402.12659/) (2024)
- [HelpSteer2-Preference: Complementing Ratings with Preferences](https://mlsanity.com/paper/2410.01257/) (2024)
- [Revolutionizing Finance with LLMs: An Overview of Applications and Insights](https://mlsanity.com/paper/2401.11641/) (2024)
- [LongCite: Enabling LLMs to Generate Fine-grained Citations in Long-context QA](https://mlsanity.com/paper/2409.02897/) (2024)
- [On Large Language Models' Hallucination with Regard to Known Facts](https://mlsanity.com/paper/2403.20009/) (2024)
- [Should We Respect LLMs? A Cross-Lingual Study on the Influence of Prompt Politeness on LLM Performance](https://mlsanity.com/paper/2402.14531/) (2024)
- [Cost-Effective Hallucination Detection for LLMs](https://mlsanity.com/paper/2407.21424/) (2024)
- [Quantifying and Attributing the Hallucination of Large Language Models via Association Analysis](https://mlsanity.com/paper/2309.05217/) (2023)
- [The AI Revolution: Opportunities and Challenges for the Finance Sector](https://mlsanity.com/paper/2308.16538/) (2023)

## Built on by (most cited first, 7 of 7)

- [Analyzing Uncertainty of LLM-as-a-Judge: Interval Evaluations with Conformal Prediction](https://mlsanity.com/paper/2509.18658/) (2025)
- [FinTrust: A Comprehensive Benchmark of Trustworthiness Evaluation in Finance Domain](https://mlsanity.com/paper/2510.15232/) (2025)
- [An Adaptive Multi Agent Bitcoin Trading System](https://mlsanity.com/paper/2510.08068/) (2025)
- [Financial Instruction Following Evaluation (FIFE)](https://mlsanity.com/paper/2512.08965/) (2025)
- [FinVerBench: Benchmark Validity and Calibration in Large Language Model Financial Statement Verification](https://mlsanity.com/paper/2605.29586/) (2026)
- [Are the Financial Reasoning from LLMs Credible? A Real World Test over Long-Horizon Statements](https://mlsanity.com/paper/2607.28661/) (2026)
- [Eliciting Intrinsic Hallucinations in LLMs via Semantically Equivalent Adversarial Attacks](https://mlsanity.com/paper/2608.04286/) (2026)

## Abstract (arXiv)

We propose a new long-context financial benchmark, FailSafeQA, designed to test the robustness and context-awareness of LLMs against six variations in human-interface interactions in LLM-based query-answer systems within finance. We concentrate on two case studies: Query Failure and Context Failure. In the Query Failure scenario, we perturb the original query to vary in domain expertise, completeness, and linguistic accuracy. In the Context Failure case, we simulate the uploads of degraded, irrelevant, and empty documents. We employ the LLM-as-a-Judge methodology with Qwen2.5-72B-Instruct and use fine-grained rating criteria to define and calculate Robustness, Context Grounding, and Compliance scores for 24 off-the-shelf models. The results suggest that although some models excel at mitigating input perturbations, they must balance robust answering with the ability to refrain from hallucinating. Notably, Palmyra-Fin-128k-Instruct, recognized as the most compliant model, maintained strong baseline performance but encountered challenges in sustaining robust predictions in 17% of test cases. On the other hand, the most robust model, OpenAI o3-mini, fabricated information in 41% of tested cases. The results demonstrate that even high-performing models have significant room for improvement and highlight the role of FailSafeQA as a tool for developing LLMs optimized for dependability in financial applications. The dataset is available at: https://huggingface.co/datasets/Writer/FailSafeQA