# Large Language Models are Skeptics: False Negative Problem of Input-conflicting Hallucination

arXiv: https://arxiv.org/abs/2406.13929 · HTML: https://mlsanity.com/paper/2406.13929/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 22 references that are in the map.
- First posted on arXiv 20 Jun 2024.

## Builds on (most cited first, 16 of 16)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [PaLM: Scaling Language Modeling with Pathways](https://mlsanity.com/paper/2204.02311/) (2022)
- [Self-Refine: Iterative Refinement with Self-Feedback](https://mlsanity.com/paper/2303.17651/) (2023)
- [BoolQ: Exploring the Surprising Difficulty of Natural Yes/No Questions](https://mlsanity.com/paper/1905.10044/) (2019)
- [Did Aristotle Use a Laptop? A Question Answering Benchmark with Implicit Reasoning Strategies](https://mlsanity.com/paper/2101.02235/) (2021)
- [A Survey of Hallucination in Large Foundation Models](https://mlsanity.com/paper/2309.05922/) (2023)
- [Enhancing Retrieval-Augmented Large Language Models with Iterative Retrieval-Generation Synergy](https://mlsanity.com/paper/2305.15294/) (2023)
- [Adaptive Chameleon or Stubborn Sloth: Revealing the Behavior of Large Language Models in Knowledge Conflicts](https://mlsanity.com/paper/2305.13300/) (2023)
- [Trusting Your Evidence: Hallucinate Less with Context-aware Decoding](https://mlsanity.com/paper/2305.14739/) (2023)
- [Sources of Hallucination by Large Language Models on Inference Tasks](https://mlsanity.com/paper/2305.14552/) (2023)
- [DDCoT: Duty-Distinct Chain-of-Thought Prompting for Multimodal Reasoning in Language Models](https://mlsanity.com/paper/2310.16436/) (2023)
- [DisentQA: Disentangling Parametric and Contextual Knowledge with Counterfactual Question Answering](https://mlsanity.com/paper/2211.05655/) (2022)
- [Language models are not naysayers: An analysis of language models on negation benchmarks](https://mlsanity.com/paper/2306.08189/) (2023)
- [Retrieve-Rewrite-Answer: A KG-to-Text Enhanced LLMs Framework for Knowledge Graph Question Answering](https://mlsanity.com/paper/2309.11206/) (2023)

## Built on by (most cited first, 4 of 4)

- [VLM2-Bench: A Closer Look at How Well VLMs Implicitly Link Explicit Matching Visual Cues](https://mlsanity.com/paper/2502.12084/) (2025)
- [Trust & Safety of LLMs and LLMs in Trust & Safety](https://mlsanity.com/paper/2412.02113/) (2024)
- [From Misleading Queries to Accurate Answers: A Three-Stage Fine-Tuning Method for LLMs](https://mlsanity.com/paper/2504.11277/) (2025)
- [ToolAlignBench: Investigating Alignment Conflicts in Tool-Calling Enabled LLMs](https://mlsanity.com/paper/2607.14285/) (2026)

## Abstract (arXiv)

In this paper, we identify a new category of bias that induces input-conflicting hallucinations, where large language models (LLMs) generate responses inconsistent with the content of the input context. This issue we have termed the false negative problem refers to the phenomenon where LLMs are predisposed to return negative judgments when assessing the correctness of a statement given the context. In experiments involving pairs of statements that contain the same information but have contradictory factual directions, we observe that LLMs exhibit a bias toward false negatives. Specifically, the model presents greater overconfidence when responding with False. Furthermore, we analyze the relationship between the false negative problem and context and query rewriting and observe that both effectively tackle false negatives in LLMs.