# AbsenceBench: Language Models Can't Tell What's Missing

arXiv: https://arxiv.org/abs/2506.11440 · HTML: https://mlsanity.com/paper/2506.11440/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 28 of its 37 references that are in the map.
- First posted on arXiv 13 Jun 2025.

## Builds on (most cited first, 28 of 28)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [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)
- [FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness](https://mlsanity.com/paper/2205.14135/) (2022)
- [FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning](https://mlsanity.com/paper/2307.08691/) (2023)
- [LongBench: A Bilingual, Multitask Benchmark for Long Context Understanding](https://mlsanity.com/paper/2308.14508/) (2023)
- [RULER: What's the Real Context Size of Your Long-Context Language Models?](https://mlsanity.com/paper/2404.06654/) (2024)
- [Transformers are SSMs: Generalized Models and Efficient Algorithms Through Structured State Space Duality](https://mlsanity.com/paper/2405.21060/) (2024)
- [Train Short, Test Long: Attention with Linear Biases Enables Input Length Extrapolation](https://mlsanity.com/paper/2108.12409/) (2021)
- [Extending Context Window of Large Language Models via Positional Interpolation](https://mlsanity.com/paper/2306.15595/) (2023)
- [The NarrativeQA Reading Comprehension Challenge](https://mlsanity.com/paper/1712.07040/) (2017)
- [Ring Attention with Blockwise Transformers for Near-Infinite Context](https://mlsanity.com/paper/2310.01889/) (2023)
- [∞Bench: Extending Long Context Evaluation Beyond 100K Tokens](https://mlsanity.com/paper/2402.13718/) (2024)
- [Mathematical Capabilities of ChatGPT](https://mlsanity.com/paper/2301.13867/) (2023)
- [ZeroSCROLLS: A Zero-Shot Benchmark for Long Text Understanding](https://mlsanity.com/paper/2305.14196/) (2023)
- [Benchmarking Cognitive Biases in Large Language Models as Evaluators](https://mlsanity.com/paper/2309.17012/) (2023)
- [How to Train Long-Context Language Models (Effectively)](https://mlsanity.com/paper/2410.02660/) (2024)
- [BooookScore: A systematic exploration of book-length summarization in the era of LLMs](https://mlsanity.com/paper/2310.00785/) (2023)
- [Unlimiformer: Long-Range Transformers with Unlimited Length Input](https://mlsanity.com/paper/2305.01625/) (2023)
- [A Length-Extrapolatable Transformer](https://mlsanity.com/paper/2212.10554/) (2022)
- [HELMET: How to Evaluate Long-Context Language Models Effectively and Thoroughly](https://mlsanity.com/paper/2410.02694/) (2024)
- [Michelangelo: Long Context Evaluations Beyond Haystacks via Latent Structure Queries](https://mlsanity.com/paper/2409.12640/) (2024)
- [Long-Context Language Modeling with Parallel Context Encoding](https://mlsanity.com/paper/2402.16617/) (2024)
- [FABLES: Evaluating faithfulness and content selection in book-length summarization](https://mlsanity.com/paper/2404.01261/) (2024)
- [Simple Hardware-Efficient Long Convolutions for Sequence Modeling](https://mlsanity.com/paper/2302.06646/) (2023)
- [NovelQA: Benchmarking Question Answering on Documents Exceeding 200K Tokens](https://mlsanity.com/paper/2403.12766/) (2024)
- [Stress-Testing Long-Context Language Models with Lifelong ICL and Task Haystack](https://mlsanity.com/paper/2407.16695/) (2024)

## Built on by (most cited first, 9 of 9)

- [Knowing What's Missing: Assessing Information Sufficiency in Question Answering](https://mlsanity.com/paper/2512.06476/) (2025)
- [Mapping Overlaps in Benchmarks through Perplexity in the Wild](https://mlsanity.com/paper/2509.23488/) (2025)
- [LLMs Remember First, Forget Last: Dual-Process Interference in Large Language Models](https://mlsanity.com/paper/2603.00270/) (2026)
- [When Absence Is Evidence: Evaluating Completeness-Sensitive Negative Reasoning in Large Language Models](https://mlsanity.com/paper/2608.04591/) (2026)
- [LLM Judges Verify Presence, Not Absence: Omission Blindness in AI Clinical Notes and What Recovers It](https://mlsanity.com/paper/2608.31016/) (2026)
- [Aligning Probabilistic Beliefs under Informative Missingness: LLM Steerability in Clinical Reasoning](https://mlsanity.com/paper/2512.00479/) (2025)
- [Mitigating hallucinations and omissions in LLMs for invertible problems: An application to hardware logic design automation](https://mlsanity.com/paper/2512.03053/) (2025)
- [TrustShiftProbe: Characterizing, Benchmarking, and Defending Staged Trust Attacks on MCP Servers](https://mlsanity.com/paper/2608.23763/) (2026)
- [No More Free Lunch: Corpus Task Complexity Matters as Corpora Grow](https://mlsanity.com/paper/2609.29245/) (2026)

## Abstract (arXiv)

Large language models (LLMs) are increasingly capable of processing long inputs and locating specific information within them, as evidenced by their performance on the Needle in a Haystack (NIAH) test. However, while models excel at recalling surprising information, they still struggle to identify clearly omitted information. We introduce AbsenceBench to assesses LLMs' capacity to detect missing information across three domains: numerical sequences, poetry, and GitHub pull requests. AbsenceBench asks models to identify which pieces of a document were deliberately removed, given access to both the original and edited contexts. Despite the apparent straightforwardness of these tasks, our experiments reveal that even state-of-the-art models like Claude-3.7-Sonnet achieve only 69.6% F1-score with a modest average context length of 5K tokens. Our analysis suggests this poor performance stems from a fundamental limitation: Transformer attention mechanisms cannot easily attend to "gaps" in documents since these absences don't correspond to any specific keys that can be attended to. Overall, our results and analysis provide a case study of the close proximity of tasks where models are already superhuman (NIAH) and tasks where models breakdown unexpectedly (AbsenceBench).