How Is LLM Reasoning Distracted by Irrelevant Context? An Analysis Using a Controlled Benchmark (2025.emnlp-main)
Copied to clipboard
| Challenge: | Prior work has not explored the mechanisms underlying this sensitivity. |
| Approach: | They propose a synthetic benchmark to evaluate Large Language Models’ reasoning robustness against systematically controlled irrelevant context (IC). |
| Outcome: | The proposed model improves in-distribution and out-of-disttribution scenarios while training with strong distractors. |
Similar Papers
GSM-Plus: A Comprehensive Benchmark for Evaluating the Robustness of LLMs as Mathematical Problem Solvers (2024.acl-long)
Copied to clipboard
| Challenge: | Large language models (LLMs) have demonstrated impressive performance across various mathematical reasoning benchmarks. |
| Approach: | They introduce an adversarial grade school math dataset and explore whether LLMs can be more robust when questions are slightly changed. |
| Outcome: | The proposed method generates and verifies each intermediate thought based on its reasoning goal and calculation result. |
Relevant or Random: Can LLMs Truly Perform Analogical Reasoning? (2025.findings-acl)
Copied to clipboard
| Challenge: | Analogical reasoning is a unique ability of humans to address unfamiliar challenges by transferring strategies from relevant past experiences. |
| Approach: | They propose to use self-generated random examples to improve performance on a variety of reasoning tasks by incorporating relevant examples from relevant past experiences. |
| Outcome: | The proposed methods achieve comparable or even better performance on GSM8K with random biological examples. |
LLMs can be easily Confused by Instructional Distractions (2025.acl-long)
Copied to clipboard
| Challenge: | Large language models (LLMs) show exceptional skill in instruction following tasks, but can become vulnerable when they are required to disregard instructions. |
| Approach: | They propose a benchmark to assess LLMs' performance under instructional distraction. |
| Outcome: | The proposed benchmark categorizes real-world instances of instructional distraction and evaluates LLMs across four instruction tasks: proofreading, rewriting, translation, and style transfer—alongside five input tasks: reasoning, code generation, mathematical reasoning, bias detection, and question answering. |
No Need for Explanations: LLMs can implicitly learn from mistakes in-context (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing literature assumes that correct answers to large language models must be accompanied by comprehensive rationales to be helpful. |
| Approach: | They propose to show incorrect answers to Large Language Models (LLMs) as a popular strategy to improve their performance in reasoning-intensive tasks. |
| Outcome: | The proposed approach outperforms chain-of-thought prompting in math reasoning tasks. |
GSM-Noise: Exploring and Enhancing Large Language Models’ Reasoning under Noisy Inputs (2026.findings-acl)
Copied to clipboard
| Challenge: | Large language models struggle when dealing with complex, ill-formed, or noisy inputs . open-source models are less robust, while closed-source ones are more robust . |
| Approach: | They propose to use GSM-Noise to refine inputs before engaging in in-depth analysis to improve LLM robustness under noisy conditions. |
| Outcome: | The proposed model can achieve consistent performance gains under noisy conditions with prompt engineering, supervised finetuning, and reinforcement learning. |
Sorting through the noise: Testing robustness of information processing in pre-trained language models (2021.emnlp-main)
Copied to clipboard
| Challenge: | Pre-trained language models have shown impressive performance on downstream NLP tasks, but we have yet to establish a clear understanding of their sophistication when it comes to processing, retaining, and applying information presented in their input. |
| Approach: | They examine how robustly pre-trained LMs retain and apply relevant context information in the face of distracting content. |
| Outcome: | The proposed models retain and use critical context information in the face of distracting content, while models are susceptible to factors of semantic similarity and word position. |
Quantifying the Influence of Irrelevant Contexts on Political Opinions Produced by LLMs (2025.acl-srw)
Copied to clipboard
| Challenge: | Recent studies have examined the generation of large language models (LLMs) on subjective topics such as political opinions and attitudinal questionnaires. |
| Approach: | They use a Political Compass Test questionnaire to quantify how irrelevant information can systematically bias model opinions in specific directions. |
| Outcome: | The results show that even seemingly unrelated contexts alter model responses in predictable ways. |
Born Pragmatic, Trained to Hallucinate? Quantifying the Origins of Contextual Bias in LLMs via the PaCE Benchmark (2026.findings-acl)
Copied to clipboard
| Challenge: | Large language models excel at capturing communicative intent, but they have a side effect: pragmatic hallucination. |
| Approach: | They propose a benchmark to quantify the impact of pragmatic hallucination on large language models . they propose RLHF and SFT to induce a strong tendency for pragmatic over-attribution . |
| Outcome: | The proposed model outperforms existing models in predicting pragmatic hallucinations . the evaluations show that current alignment paradigms lack precise control over pragmatic boundaries . |
Assessing “Implicit” Retrieval Robustness of Large Language Models (2024.emnlp-main)
Copied to clipboard
| Challenge: | Retrieval-augmented generation (RAG) is a framework to enhance large language models with external knowledge, but its effectiveness is constrained by the retrieval robustness of the model. |
| Approach: | They propose to use gold and distracting context to fine-tune models to handle relevant or irrelevant retrieved context in an end-to-end manner. |
| Outcome: | The proposed model performs better when gold and distracting context are used, while still extracting correct answers when retrieval is accurate. |
Stochastic Chameleons: Irrelevant Context Hallucinations Reveal Class-Based (Mis)Generalization in LLMs (2025.acl-long)
Copied to clipboard
| Challenge: | Existing studies have shown that LLMs reproduce training artifacts, exploit spurious correlations, and fail when faced with distribution shifts. |
| Approach: | They examine irrelevant context hallucinations in which models integrate misleading contextual cues into their predictions. |
| Outcome: | The proposed model errors are reflected in the model's internal computations, and they are consistent with previous studies. |