Understanding the Dynamics of Demonstration Conflict in In-Context Learning

• URL: http://arxiv.org/abs/2603.04464v1
• Date: Tue, 03 Mar 2026 20:00:33 GMT
• Title: Understanding the Dynamics of Demonstration Conflict in In-Context Learning
• Authors: Difan Jiao, Di Wang, Lijie Hu,
• Abstract summary: In-context learning enables large language models to perform novel tasks through few-shot demonstrations.<n>We study demonstration-dependent tasks requiring models to infer underlying patterns, a process we characterize as rule inference.<n>We find that models suffer substantial performance degradation from a single demonstration with corrupted rule.
• Score: 14.115388433771786
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: In-context learning enables large language models to perform novel tasks through few-shot demonstrations. However, demonstrations per se can naturally contain noise and conflicting examples, making this capability vulnerable. To understand how models process such conflicts, we study demonstration-dependent tasks requiring models to infer underlying patterns, a process we characterize as rule inference. We find that models suffer substantial performance degradation from a single demonstration with corrupted rule. This systematic misleading behavior motivates our investigation of how models process conflicting evidence internally. Using linear probes and logit lens analysis, we discover that under corruption models encode both correct and incorrect rules in intermediate layers but develop prediction confidence only in late layers, revealing a two-phase computational structure. We then identify attention heads for each phase underlying the reasoning failures: Vulnerability Heads in early-to-middle layers exhibit positional attention bias with high sensitivity to corruption, while Susceptible Heads in late layers significantly reduce support for correct predictions when exposed to the corrupted evidence. Targeted ablation validates our findings, with masking a small number of identified heads improving performance by over 10%.

Related papers

• Analyzing Reasoning Consistency in Large Multimodal Models under Cross-Modal Conflicts [74.47786985522762]
  We identify a critical failure mode termed textual inertia, where models tend to blindly adhere to the erroneous text while neglecting conflicting visual evidence.<n>We propose the LogicGraph Perturbation Protocol that structurally injects perturbations into the reasoning chains of diverse LMMs.<n>Results reveal that models successfully self-correct in less than 10% of cases and predominantly succumb to blind textual error propagation.
  arXiv  Detail & Related papers  (2026-01-07T16:39:34Z)
• Detecting Regional Spurious Correlations in Vision Transformers via Token Discarding [0.7315240103690552]
  We present a novel method to detect spurious correlations in vision transformers.<n>We also present a case study investigating spurious signals in invasive breast mass classification.
  arXiv  Detail & Related papers  (2025-09-04T08:40:40Z)
• Learning to Focus: Causal Attention Distillation via Gradient-Guided Token Pruning [62.23671919314693]
  Large language models (LLMs) have demonstrated significant improvements in contextual understanding.<n>However, their ability to attend to truly critical information during long-context reasoning and generation still falls behind the pace.<n>We introduce a two-stage framework called Learning to Focus (LeaF) to mitigate confounding factors.
  arXiv  Detail & Related papers  (2025-06-09T15:16:39Z)
• Causality can systematically address the monsters under the bench(marks) [64.36592889550431]
  Benchmarks are plagued by various biases, artifacts, or leakage.<n>Models may behave unreliably due to poorly explored failure modes.<n> causality offers an ideal framework to systematically address these challenges.
  arXiv  Detail & Related papers  (2025-02-07T17:01:37Z)
• Adversarial Transferability in Deep Denoising Models: Theoretical Insights and Robustness Enhancement via Out-of-Distribution Typical Set Sampling [6.189440665620872]
  Deep learning-based image denoising models demonstrate remarkable performance, but their lack of robustness analysis remains a significant concern.<n>A major issue is that these models are susceptible to adversarial attacks, where small, carefully crafted perturbations to input data can cause them to fail.<n>We propose a novel adversarial defense method: the Out-of-Distribution Typical Set Sampling Training strategy.
  arXiv  Detail & Related papers  (2024-12-08T13:47:57Z)
• Extreme Miscalibration and the Illusion of Adversarial Robustness [66.29268991629085]
  Adversarial Training is often used to increase model robustness. We show that this observed gain in robustness is an illusion of robustness (IOR) We urge the NLP community to incorporate test-time temperature scaling into their robustness evaluations.
  arXiv  Detail & Related papers  (2024-02-27T13:49:12Z)
• Overthinking the Truth: Understanding how Language Models Process False Demonstrations [32.29658741345911]
  We study harmful imitation through the lens of a model's internal representations. We identify two related phenomena: "overthinking" and "false induction heads"
  arXiv  Detail & Related papers  (2023-07-18T17:56:50Z)
• Causal Analysis for Robust Interpretability of Neural Networks [0.2519906683279152]
  We develop a robust interventional-based method to capture cause-effect mechanisms in pre-trained neural networks. We apply our method to vision models trained on classification tasks.
  arXiv  Detail & Related papers  (2023-05-15T18:37:24Z)
• Causal Triplet: An Open Challenge for Intervention-centric Causal Representation Learning [98.78136504619539]
  Causal Triplet is a causal representation learning benchmark featuring visually more complex scenes. We show that models built with the knowledge of disentangled or object-centric representations significantly outperform their distributed counterparts.
  arXiv  Detail & Related papers  (2023-01-12T17:43:38Z)
• Fairness Increases Adversarial Vulnerability [50.90773979394264]
  This paper shows the existence of a dichotomy between fairness and robustness, and analyzes when achieving fairness decreases the model robustness to adversarial samples. Experiments on non-linear models and different architectures validate the theoretical findings in multiple vision domains. The paper proposes a simple, yet effective, solution to construct models achieving good tradeoffs between fairness and robustness.
  arXiv  Detail & Related papers  (2022-11-21T19:55:35Z)
• Probing Representation Forgetting in Supervised and Unsupervised Continual Learning [14.462797749666992]
  Catastrophic forgetting is associated with an abrupt loss of knowledge previously learned by a model. We show that representation forgetting can lead to new insights on the effect of model capacity and loss function used in continual learning.
  arXiv  Detail & Related papers  (2022-03-24T23:06:08Z)
• Firearm Detection via Convolutional Neural Networks: Comparing a Semantic Segmentation Model Against End-to-End Solutions [68.8204255655161]
  Threat detection of weapons and aggressive behavior from live video can be used for rapid detection and prevention of potentially deadly incidents. One way for achieving this is through the use of artificial intelligence and, in particular, machine learning for image analysis. We compare a traditional monolithic end-to-end deep learning model and a previously proposed model based on an ensemble of simpler neural networks detecting fire-weapons via semantic segmentation.
  arXiv  Detail & Related papers  (2020-12-17T15:19:29Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.