# How Is LLM Reasoning Distracted by Irrelevant Context? An Analysis Using a Controlled Benchmark

arXiv: https://arxiv.org/abs/2505.18761 · HTML: https://mlsanity.com/paper/2505.18761/

## Key facts

- Cited by 28 papers in the map (data through 14 Oct 2026).
- Placed in Mathematical reasoning, one of 17 directions in LLM reasoning.
- Builds on 29 of its 50 references that are in the map.
- First posted on arXiv 24 May 2025.

## Placed in

- LLM reasoning / [Mathematical reasoning](https://mlsanity.com/lr/mathematical-reasoning/)

## Builds on (most cited first, 29 of 29)

- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [Tree of Thoughts: Deliberate Problem Solving with Large Language Models](https://mlsanity.com/paper/2305.10601/) (2023)
- [Least-to-Most Prompting Enables Complex Reasoning in Large Language Models](https://mlsanity.com/paper/2205.10625/) (2022)
- [Solving Quantitative Reasoning Problems with Language Models](https://mlsanity.com/paper/2206.14858/) (2022)
- [Large Language Models Cannot Self-Correct Reasoning Yet](https://mlsanity.com/paper/2310.01798/) (2023)
- [STaR: Bootstrapping Reasoning With Reasoning](https://mlsanity.com/paper/2203.14465/) (2022)
- [Solving math word problems with process- and outcome-based feedback](https://mlsanity.com/paper/2211.14275/) (2022)
- [Training Language Models to Self-Correct via Reinforcement Learning](https://mlsanity.com/paper/2409.12917/) (2024)
- [The Reversal Curse: LLMs trained on "A is B" fail to learn "B is A"](https://mlsanity.com/paper/2309.12288/) (2023)
- [ProofWriter: Generating Implications, Proofs, and Abductive Statements over Natural Language](https://mlsanity.com/paper/2012.13048/) (2020)
- [ProcessBench: Identifying Process Errors in Mathematical Reasoning](https://mlsanity.com/paper/2412.06559/) (2024)
- [LongLoRA: Efficient Fine-tuning of Long-Context Large Language Models](https://mlsanity.com/paper/2309.12307/) (2023)
- [V-STaR: Training Verifiers for Self-Taught Reasoners](https://mlsanity.com/paper/2402.06457/) (2024)
- [ART: Automatic multi-step reasoning and tool-use for large language models](https://mlsanity.com/paper/2303.09014/) (2023)
- [QA-LoRA: Quantization-Aware Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2309.14717/) (2023)
- [Physics of Language Models: Part 3.3, Knowledge Capacity Scaling Laws](https://mlsanity.com/paper/2404.05405/) (2024)
- [Physics of Language Models: Part 3.2, Knowledge Manipulation](https://mlsanity.com/paper/2309.14402/) (2023)
- [Pride and Prejudice: LLM Amplifies Self-Bias in Self-Refinement](https://mlsanity.com/paper/2402.11436/) (2024)
- [LongRAG: Enhancing Retrieval-Augmented Generation with Long-context LLMs](https://mlsanity.com/paper/2406.15319/) (2024)
- [Physics of Language Models: Part 1, Learning Hierarchical Language Structures](https://mlsanity.com/paper/2305.13673/) (2023)
- [How Easily do Irrelevant Inputs Skew the Responses of Large Language Models?](https://mlsanity.com/paper/2404.03302/) (2024)
- [MMDocIR: Benchmarking Multimodal Retrieval for Long Documents](https://mlsanity.com/paper/2501.08828/) (2025)
- [Benchmarking Retrieval-Augmented Multimodal Generation for Document Question Answering](https://mlsanity.com/paper/2505.16470/) (2025)
- [RAG-Instruct: Boosting LLMs with Diverse Retrieval-Augmented Instructions](https://mlsanity.com/paper/2501.00353/) (2024)
- [GSM-Infinite: How Do Your LLMs Behave over Infinitely Increasing Context Length and Reasoning Complexity?](https://mlsanity.com/paper/2502.05252/) (2025)
- [Cutting Through the Noise: Boosting LLM Performance on Math Word Problems](https://mlsanity.com/paper/2406.15444/) (2024)
- [Enhancing Robustness in Large Language Models: Prompting for Mitigating the Impact of Irrelevant Information](https://mlsanity.com/paper/2408.10615/) (2024)
- [UTMath: Math Evaluation with Unit Test via Reasoning-to-Coding Thoughts](https://mlsanity.com/paper/2411.07240/) (2024)
- [VCSearch: Bridging the Gap Between Well-Defined and Ill-Defined Problems in Mathematical Reasoning](https://mlsanity.com/paper/2406.05055/) (2024)

## Built on by (most cited first, 28 of 28)

- [A Survey of Process Reward Models: From Outcome Signals to Process Supervisions for Large Language Models](https://mlsanity.com/paper/2510.08049/) (2025)
- [HS-STaR: Hierarchical Sampling for Self-Taught Reasoners via Difficulty Estimation and Budget Reallocation](https://mlsanity.com/paper/2505.19866/) (2025)
- [Are Tools All We Need? Unveiling the Tool-Use Tax in LLM Agents](https://mlsanity.com/paper/2605.00136/) (2026)
- [Make Each Token Count: Towards Improving Long-Context Performance with KV Cache Eviction](https://mlsanity.com/paper/2605.09649/) (2026)
- [Position Bias Mitigates Position Bias:Mitigate Position Bias Through Inter-Position Knowledge Distillation](https://mlsanity.com/paper/2508.15709/) (2025)
- [Shallow Robustness, Deep Vulnerabilities: Multi-Turn Evaluation of Medical LLMs](https://mlsanity.com/paper/2510.12255/) (2025)
- [Humanity's Last Code Exam: Can Advanced LLMs Conquer Human's Hardest Code Competition?](https://mlsanity.com/paper/2506.12713/) (2025)
- [DTS: Enhancing Large Reasoning Models via Decoding Tree Sketching](https://mlsanity.com/paper/2511.00640/) (2025)
- [Thinking in a Crowd: How Auxiliary Information Shapes LLM Reasoning](https://mlsanity.com/paper/2509.18163/) (2025)
- [The Regression Tax: Decomposing Why Skills Help and Hurt LLM Agents](https://mlsanity.com/paper/2607.22520/) (2026)
- [A Survey of Link Prediction in N-ary Knowledge Graphs](https://mlsanity.com/paper/2506.08970/) (2025)
- [Chain-of-Trigger: An Agentic Backdoor that Paradoxically Enhances Agentic Robustness](https://mlsanity.com/paper/2510.08238/) (2025)
- [Diagnosing and Mitigating Context Rot in Long-horizon Search](https://mlsanity.com/paper/2606.29718/) (2026)
- [Diagnosis Before Recovery: Turning Agent Failures into Selective Self-Correction](https://mlsanity.com/paper/2608.11772/) (2026)
- [LongWeave: A Long-Form Generation Benchmark Bridging Real-World Relevance and Verifiability](https://mlsanity.com/paper/2510.24345/) (2025)
- [Understanding LLM Performance Degradation in Multi-Instance Processing: The Roles of Instance Count and Context Length](https://mlsanity.com/paper/2603.22608/) (2026)
- [The Illusion of Robustness: Aggregate Accuracy Hides Prediction Flips under Task-Irrelevant Context](https://mlsanity.com/paper/2607.12963/) (2026)
- [LoRA-PAR: A Flexible Dual-System LoRA Partitioning Approach to Efficient LLM Fine-Tuning](https://mlsanity.com/paper/2507.20999/) (2025)
- [The Model Says Walk: How Surface Heuristics Override Implicit Constraints in LLM Reasoning](https://mlsanity.com/paper/2603.29025/) (2026)
- [Purifying Multimodal Retrieval: Fragment-Level Evidence Selection for RAG](https://mlsanity.com/paper/2604.27600/) (2026)
- [Enhancing Mathematical Problem Solving in LLMs through Execution-Driven Reasoning Augmentation](https://mlsanity.com/paper/2602.03950/) (2026)
- [Learning Evidence Highlighting for Frozen LLMs](https://mlsanity.com/paper/2604.22565/) (2026)
- [Multilingual Reasoning Cascades Need More Context](https://mlsanity.com/paper/2606.27306/) (2026)
- [Implicit Reasoning Steering via Concept Chaining](https://mlsanity.com/paper/2607.14242/) (2026)
- [Evaluating Context Segmentation in Locally Deployable SLMs for Cybersecurity CTF Tasks](https://mlsanity.com/paper/2609.12839/) (2026)
- [Surprising Effectiveness of Self-Demonstrations in Enhancing Schema-Ontology Mapping with LLMs](https://mlsanity.com/paper/2609.13776/) (2026)
- [AwarenessBench: Assessing Cognitive Capabilities of Language Models](https://mlsanity.com/paper/2609.35409/) (2026)
- [State Representation Shapes Long-Horizon Agent Learning and Transfer: An Empirical Study](https://mlsanity.com/paper/2610.15407/) (2026)

## Abstract (arXiv)

We introduce Grade School Math with Distracting Context (GSM-DC), a synthetic benchmark to evaluate Large Language Models' (LLMs) reasoning robustness against systematically controlled irrelevant context (IC). GSM-DC constructs symbolic reasoning graphs with precise distractor injections, enabling rigorous, reproducible evaluation. Our experiments demonstrate that LLMs are significantly sensitive to IC, affecting both reasoning path selection and arithmetic accuracy. Additionally, training models with strong distractors improves performance in both in-distribution and out-of-distribution scenarios. We further propose a stepwise tree search guided by a process reward model, which notably enhances robustness in out-of-distribution conditions.