PromptCD: Test-Time Behavior Enhancement via Polarity-Prompt Contrastive Decoding

• URL: http://arxiv.org/abs/2602.20696v1
• Date: Tue, 24 Feb 2026 08:56:52 GMT
• Title: PromptCD: Test-Time Behavior Enhancement via Polarity-Prompt Contrastive Decoding
• Authors: Baolong Bi, Yuyao Ge, Shenghua Liu, Yuchen He, Siqian Tong, Lizhe Chen, Lingrui Mei, Zehao Li, Yiwei Wang, Yujun Cai, Ming-Hsuan Yang, Xueqi Cheng,
• Abstract summary: We introduce Polarity-Prompt Contrastive Decoding (PromptCD), a test-time behavior control method that generalizes contrastive decoding to broader enhancement settings.<n>PromptCD constructs paired positive and negative guiding prompts for a target behavior and contrasts model responses to reinforce desirable outcomes.<n>Experiments on the "3H" alignment objectives demonstrate consistent and substantial improvements, indicating that post-trained models can achieve meaningful self-enhancement purely at test time.
• Score: 85.22047087898311
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Reliable AI systems require large language models (LLMs) to exhibit behaviors aligned with human preferences and values. However, most existing alignment approaches operate at training time and rely on additional high-quality data, incurring significant computational and annotation costs. While recent work has shown that contrastive decoding can leverage a model's internal distributions to improve specific capabilities, its applicability remains limited to narrow behavioral scopes and scenarios. In this work, we introduce Polarity-Prompt Contrastive Decoding (PromptCD), a test-time behavior control method that generalizes contrastive decoding to broader enhancement settings. PromptCD constructs paired positive and negative guiding prompts for a target behavior and contrasts model responses-specifically token-level probability distributions in LLMs and visual attention patterns in VLMs-to reinforce desirable outcomes. This formulation extends contrastive decoding to a wide range of enhancement objectives and is applicable to both LLMs and Vision-Language Models (VLMs) without additional training. For LLMs, experiments on the "3H" alignment objectives (helpfulness, honesty, and harmlessness) demonstrate consistent and substantial improvements, indicating that post-trained models can achieve meaningful self-enhancement purely at test time. For VLMs, we further analyze contrastive effects on visual attention, showing that PromptCD significantly improves VQA performance by reinforcing behavior-consistent visual grounding. Collectively, these results highlight PromptCD as a simple, general, and cost-efficient strategy for reliable behavior control across modalities.

Related papers

• Guiding Diffusion-based Reconstruction with Contrastive Signals for Balanced Visual Representation [81.40978077888693]
  Contrastive Language-Image Pre-training (CLIP) has become a key bottleneck for downstream performance.<n>Recent solutions use diffusion models to enhance representations by conditioning image reconstruction on CLIP visual tokens.<n>We integrate contrastive signals into diffusion-based reconstruction to pursue more comprehensive visual representations.
  arXiv  Detail & Related papers  (2026-03-05T04:45:49Z)
• Revealing and Enhancing Core Visual Regions: Harnessing Internal Attention Dynamics for Hallucination Mitigation in LVLMs [67.69730908817321]
  Internal Positive Attention Dynamics (PAD) in LVLMs naturally reveal semantically core visual regions under the distortions of attention sinks.<n>We propose Positive Attention Dynamics Enhancement (PADE), a training-free attention intervention that constructs a PAD map to identify semantically core visual regions.
  arXiv  Detail & Related papers  (2026-02-17T13:08:06Z)
• Adaptive Residual-Update Steering for Low-Overhead Hallucination Mitigation in Large Vision Language Models [13.32858759983739]
  Large Vision-Language Models (LVLMs) often suffer from object hallucination, generating text inconsistent with visual inputs.<n>Existing inference-time interventions to mitigate this issue present a challenging trade-off.<n>We present Residual-Update Directed DEcoding Regulation (RUDDER), a framework that steers LVLMs towards visually-grounded generation.
  arXiv  Detail & Related papers  (2025-11-13T13:29:38Z)
• Beyond Single Models: Mitigating Multimodal Hallucinations via Adaptive Token Ensemble Decoding [41.828387997311474]
  Large Vision-Language Models (LVLMs) have recently achieved impressive results in multimodal tasks such as image captioning and visual question answering.<n>They remain prone to object hallucination -- generating descriptions of nonexistent or misidentified objects.<n>We propose Adaptive Token Ensemble Decoding (ATED), a training-free, token-level ensemble framework that mitigates hallucination by aggregating predictions from multiple LVLMs during inference.
  arXiv  Detail & Related papers  (2025-10-21T06:11:24Z)
• Agentic Jigsaw Interaction Learning for Enhancing Visual Perception and Reasoning in Vision-Language Models [63.69856480318313]
  AGILE formulates jigsaw solving as an interactive process, enabling the model to progressively engage with the environment.<n>We show that AGILE substantially boosts performance on jigsaw tasks of varying complexity.<n>We also demonstrate strong generalization across 9 general vision tasks, achieving an average improvement of 3.1%.
  arXiv  Detail & Related papers  (2025-10-01T17:58:05Z)
• Improving vulnerability type prediction and line-level detection via adversarial training-based data augmentation and multi-task learning [10.375389754684905]
  We propose a unified approach that integrates Embedding-Layer Driven Adversarial Training (EDAT) with Multi-task Learning (MTL)<n>Our proposed approach outperforms state-of-the-art baselines on both Vulnerability Type Prediction (VTP) and Line-level Vulnerability Detection (LVD) tasks.
  arXiv  Detail & Related papers  (2025-06-30T05:47:09Z)
• Mitigating Hallucination of Large Vision-Language Models via Dynamic Logits Calibration [8.192590936983347]
  Large Vision-Language Models (LVLMs) have demonstrated significant advancements in multimodal understanding.<n>They are frequently hampered by hallucination-the generation of text that contradicts visual input.<n>Existing training-free decoding strategies exhibit critical limitations.<n>This paper introduces Dynamic Logits (DLC), a novel training-free decoding framework designed to align text generation with visual evidence at inference time.
  arXiv  Detail & Related papers  (2025-06-26T17:35:40Z)
• Calibrated Self-Rewarding Vision Language Models [27.686545023186852]
  Large Vision-Language Models (LVLMs) have made substantial progress by integrating pre-trained large language models (LLMs) and vision models through instruction tuning. LVLMs often exhibit the hallucination phenomenon, where generated text responses appear linguistically plausible but contradict the input image. We propose the Calibrated Self-Rewarding (CSR) approach, which enables the model to self-improve by iteratively generating candidate responses, evaluating the reward for each response, and curating preference data for fine-tuning.
  arXiv  Detail & Related papers  (2024-05-23T14:30:33Z)
• Debiasing Multimodal Large Language Models via Penalization of Language Priors [38.97645845493758]
  Multimodal Large Language Models (MLLMs) have become indispensable tools in computer vision and natural language processing.<n>Despite their advancements, our investigation reveals a noteworthy bias: the generated content is often driven more by the inherent priors of the underlying Large Language Models (LLMs) than by the input image.<n>We propose two simple, training-free strategies to rectify these biases and redirect the model's focus toward visual information.
  arXiv  Detail & Related papers  (2024-03-08T12:35:07Z)
• Prompt Highlighter: Interactive Control for Multi-Modal LLMs [50.830448437285355]
  This study targets a critical aspect of multi-modal LLMs' (LLMs&VLMs) inference: explicit controllable text generation. We introduce a novel inference method, Prompt Highlighter, which enables users to highlight specific prompt spans to interactively control the focus during generation. We find that, during inference, guiding the models with highlighted tokens through the attention weights leads to more desired outputs.
  arXiv  Detail & Related papers  (2023-12-07T13:53:29Z)
• Robust Pre-Training by Adversarial Contrastive Learning [120.33706897927391]
  Recent work has shown that, when integrated with adversarial training, self-supervised pre-training can lead to state-of-the-art robustness. We improve robustness-aware self-supervised pre-training by learning representations consistent under both data augmentations and adversarial perturbations.
  arXiv  Detail & Related papers  (2020-10-26T04:44:43Z)

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.