DeCoVec: Building Decoding Space based Task Vector for Large Language Models via In-Context Learning

• URL: http://arxiv.org/abs/2604.11129v1
• Date: Mon, 13 Apr 2026 07:42:54 GMT
• Title: DeCoVec: Building Decoding Space based Task Vector for Large Language Models via In-Context Learning
• Abstract summary: textscDeCoVec captures the task essence as the difference between the output logit distributions of few-shot and zero-shot prompts.<n>textscDeCoVec consistently outperforms standard few-shot baselines, with gains up to +5.50 average accuracy.
• Score: 6.461940812531588
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Task vectors, representing directions in model or activation spaces that encode task-specific behaviors, have emerged as a promising tool for steering large language models (LLMs). However, existing approaches typically require fine-tuning or invasive manipulation of internal states, limiting their flexibility and scalability. We propose \textsc{DeCoVec} (Decoding Space based Task Vector), a training-free and non-invasive framework that constructs task vectors directly in the \textit{decoding space} by leveraging in-context learning (ICL). Specifically, \textsc{DeCoVec} captures the task essence as the difference between the output logit distributions of few-shot and zero-shot prompts, then steers generation by injecting this vector into the decoding process. Experiments across seven LLMs (0.5B--9B) on TruthfulQA, Math-500, and AQUA-RAT show that \textsc{DeCoVec} consistently outperforms standard few-shot baselines, with gains up to +5.50 average accuracy. Further analysis demonstrates that \textsc{DeCoVec} effectively suppresses generation degeneration and logical flaws while exhibiting strong robustness to demonstration ordering, all without incurring additional input token costs. Our method offers a training-free and non-invasive solution for LLM steering without requiring weight updates or auxiliary models.

Related papers

• PACT: Preserving Anchored Cores in Task-vectors for Model Merging [68.52455853496585]
  Model merging aims to combine multiple task-specific fine-tuned models into a single multi-task model.<n>Most existing model merging approaches follow the Task Arithmetic paradigm.<n>We propose PACT, which preserves the anchored task-specific cores (i.e., LBW dimensions) within task vectors by aligning their complements with the subspace of the pre-trained weights.
  arXiv  Detail & Related papers  (2026-06-17T02:48:35Z)
• Distributional Alignment as a Criterion for Designing Task Vectors in In-Context Learning [6.840854574584369]
  In this paper, we argue that inference using task vectors should align their predictive distribution with that of ICL.<n>We introduce $d_textNTP$, a metric that measures the discrepancy in next-token probabilities between task vector-based and ICL-based inference.<n>We develop Linear Task Vector (LTV), a method designed to minimize $d_textNTP$ via a closed-form linear mapping.
  arXiv  Detail & Related papers  (2026-05-20T05:26:38Z)
• Language-based Trial and Error Falls Behind in the Era of Experience [50.503828360874536]
  Large Language Models (LLMs) excel in language-based agentic tasks, but their applicability to unseen, nonlinguistic environments remains limited.<n>In this work, we demonstrate the primary bottleneck is the prohibitive cost of exploration.<n>We propose SCOUT, a novel framework that decouples exploration from semantic exploitation.
  arXiv  Detail & Related papers  (2026-01-29T14:08:41Z)
• SWE-Pruner: Self-Adaptive Context Pruning for Coding Agents [32.69890220986935]
  We propose SWE-Pruner, a self-adaptive context pruning framework for coding agents.<n>SWE-Pruner performs task-aware adaptive pruning for long contexts.<n>It achieves 23-54% token reduction on agent tasks like SWE-Bench Verified and up to 14.84x compression on single-turn tasks like LongCodeQA.
  arXiv  Detail & Related papers  (2026-01-23T13:51:59Z)
• Where and What Matters: Sensitivity-Aware Task Vectors for Many-Shot Multimodal In-Context Learning [57.082554323521464]
  We propose a Sensitivity-aware Task Vector insertion framework (STV) to figure out where and what to insert.<n>Our key insight is that activation deltas across query-context pairs exhibit consistent structural patterns, providing a reliable cue for insertion.<n>Based on the identified sensitive-aware locations, we construct a pre-clustered activation bank for each location by clustering the activation values, and then apply reinforcement learning to choose the most suitable one to insert.
  arXiv  Detail & Related papers  (2025-11-11T13:42:13Z)
• Adaptive Task Vectors for Large Language Models [14.108866468832623]
  Adaptive Task Vectors (ATV) is a simple and effective framework that dynamically generates task vectors conditioned on each input query.<n>ATV demonstrates strong performance and generalization capabilities, even for unseen tasks.
  arXiv  Detail & Related papers  (2025-06-03T22:12:28Z)
• Self-Training Elicits Concise Reasoning in Large Language Models [23.475414693530965]
  Chain-of-thought (CoT) reasoning has enabled large language models (LLMs) to utilize additional computation through intermediate tokens.<n>We propose simple fine-tuning methods which leverage self-generated concise reasoning paths.<n>Our method achieves a 30% reduction in output tokens, across five model families on GSM8K and MATH, while maintaining average accuracy.
  arXiv  Detail & Related papers  (2025-02-27T14:14:50Z)
• Enhancing Input-Label Mapping in In-Context Learning with Contrastive Decoding [71.01099784480597]
  Large language models (LLMs) excel at a range of tasks through in-context learning (ICL)<n>We introduce In-Context Contrastive Decoding (ICCD), a novel method that emphasizes input-label mapping.
  arXiv  Detail & Related papers  (2025-02-19T14:04:46Z)
• Multi-Task Model Merging via Adaptive Weight Disentanglement [69.7292615212444]
  We introduce an Adaptive Weight Disentanglement method for model merging.<n>We successfully extract redundant vectors, and after their subtraction, the task vectors retain robust performance.
  arXiv  Detail & Related papers  (2024-11-27T20:08:55Z)
• Reference Trustable Decoding: A Training-Free Augmentation Paradigm for Large Language Models [79.41139393080736]
  Large language models (LLMs) have rapidly advanced and demonstrated impressive capabilities. In-Context Learning (ICL) and. Efficient Fine-Tuning (PEFT) are currently two mainstream methods for augmenting. LLMs to downstream tasks. We propose Reference Trustable Decoding (RTD), a paradigm that allows models to quickly adapt to new tasks without fine-tuning.
  arXiv  Detail & Related papers  (2024-09-30T10:48:20Z)
• Get my drift? Catching LLM Task Drift with Activation Deltas [55.75645403965326]
  Task drift allows attackers to exfiltrate data or influence the LLM's output for other users.<n>We show that a simple linear classifier can detect drift with near-perfect ROC AUC on an out-of-distribution test set.<n>We observe that this approach generalizes surprisingly well to unseen task domains, such as prompt injections, jailbreaks, and malicious instructions.
  arXiv  Detail & Related papers  (2024-06-02T16:53:21Z)
• InferAligner: Inference-Time Alignment for Harmlessness through Cross-Model Guidance [56.184255657175335]
  We develop textbfInferAligner, a novel inference-time alignment method that utilizes cross-model guidance for harmlessness alignment. Experimental results show that our method can be very effectively applied to domain-specific models in finance, medicine, and mathematics. It significantly diminishes the Attack Success Rate (ASR) of both harmful instructions and jailbreak attacks, while maintaining almost unchanged performance in downstream tasks.
  arXiv  Detail & Related papers  (2024-01-20T10:41:03Z)
• Adapting Language Models to Compress Contexts [71.98287002918941]
  Transformer-based language models (LMs) are powerful and widely-applicable tools, but their usefulness is constrained by a finite context window. We propose to adapt pre-trained LMs into AutoCompressors, which are capable of compressing long contexts into compact summary vectors. We fine-tune OPT and Llama-2 models on sequences of up to 30,720 tokens and show that AutoCompressors can utilize long contexts to improve perplexity.
  arXiv  Detail & Related papers  (2023-05-24T06:42:44Z)

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.