Summarize Before You Speak with ARACH: A Training-Free Inference-Time Plug-In for Enhancing LLMs via Global Attention Reallocation

• URL: http://arxiv.org/abs/2603.11067v1
• Date: Tue, 10 Mar 2026 06:07:54 GMT
• Title: Summarize Before You Speak with ARACH: A Training-Free Inference-Time Plug-In for Enhancing LLMs via Global Attention Reallocation
• Abstract summary: Large language models (LLMs) achieve remarkable performance, yet further gains often require costly training.<n>This has motivated growing interest in post-training techniques-especially training-free approaches that improve models at inference time without updating weights.<n>We propose ARACH(Attention Reallocation via an Adaptive Context Hub), a training-free inference-time plug-in that augments LLMs with an adaptive context hub to aggregate context and reallocate attention.
• Score: 9.508727214134106
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Large language models (LLMs) achieve remarkable performance, yet further gains often require costly training. This has motivated growing interest in post-training techniques-especially training-free approaches that improve models at inference time without updating weights. Most training-free methods treat the model as a black box and improve outputs via input/output-level interventions, such as prompt design and test-time scaling through repeated sampling, reranking/verification, or search. In contrast, they rarely offer a plug-and-play mechanism to intervene in a model's internal computation. We propose ARACH(Attention Reallocation via an Adaptive Context Hub), a training-free inference-time plug-in that augments LLMs with an adaptive context hub to aggregate context and reallocate attention. Extensive experiments across multiple language modeling tasks show consistent improvements with modest inference overhead and no parameter updates. Attention analyses further suggest that ARACH mitigates the attention sink phenomenon. These results indicate that engineering a model's internal computation offers a distinct inference-time strategy, fundamentally different from both prompt-based test-time methods and training-based post-training approaches.

Related papers

• Bagging-Based Model Merging for Robust General Text Embeddings [73.51674133699196]
  General-purpose text embedding models underpin a wide range of NLP and information retrieval applications.<n>We present a systematic study of multi-task training for text embeddings from two perspectives: data scheduling and model merging.<n>We propose Bagging-based rObust mOdel Merging (BOOM), which trains multiple embedding models on sampled subsets and merges them into a single model.
  arXiv  Detail & Related papers  (2026-02-05T15:45:08Z)
• DiRL: An Efficient Post-Training Framework for Diffusion Language Models [54.405206032785706]
  Diffusion Language Models (dLLMs) have emerged as promising alternatives to Auto-Regressive (AR) models.<n>Existing methods suffer from computational inefficiency and objective mismatches between training and inference.<n>We introduce DiRL, an efficient post-training framework that tightly integrates FlexAttention-accelerated blockwise training with LMDeploy-optimized inference.
  arXiv  Detail & Related papers  (2025-12-23T08:33:19Z)
• DiFFPO: Training Diffusion LLMs to Reason Fast and Furious via Reinforcement Learning [37.20873499361773]
  We propose a unified framework for training masked diffusion large language models (dLLMs) to reason better (furious)<n>We first unify the existing baseline approach by proposing to train surrogate policies via off-policy RL, whose likelihood is much more tractable as an approximation to the true dLLM policy.<n>We also propose a new direction of joint training efficient samplers/controllers of dLLMs policy. Via RL, we incentivize dLLMs' natural multi-token prediction capabilities by letting the model learn to adaptively allocate an inference threshold for each prompt.
  arXiv  Detail & Related papers  (2025-10-02T16:57:24Z)
• Agentic Reinforced Policy Optimization [66.96989268893932]
  Large-scale reinforcement learning with verifiable rewards (RLVR) has demonstrated its effectiveness in harnessing the potential of large language models (LLMs) for single-turn reasoning tasks.<n>Current RL algorithms inadequately balance the models' intrinsic long-horizon reasoning capabilities and their proficiency in multi-turn tool interactions.<n>We propose Agentic Reinforced Policy Optimization (ARPO), a novel agentic RL algorithm tailored for training multi-turn LLM-based agents.
  arXiv  Detail & Related papers  (2025-07-26T07:53:11Z)
• Can Prompt Difficulty be Online Predicted for Accelerating RL Finetuning of Reasoning Models? [65.18157595903124]
  This work investigates iterative approximate evaluation for arbitrary prompts.<n>It introduces Model Predictive Prompt Selection (MoPPS), a Bayesian risk-predictive framework.<n>MoPPS reliably predicts prompt difficulty and accelerates training with significantly reduced rollouts.
  arXiv  Detail & Related papers  (2025-07-07T03:20:52Z)
• Incentivizing LLMs to Self-Verify Their Answers [22.387551134333084]
  We propose a framework that incentivizes Large Language Models to self-verify their own answers.<n>We train our self-verification models based on Qwen2.5-Math-7B and DeepSeek-R1-Distill-Qwen-1.5B.<n> Experiments on multiple mathematical reasoning benchmarks show that our models can not only improve post-training performance but also enable effective test-time scaling.
  arXiv  Detail & Related papers  (2025-06-02T06:54:29Z)
• LLM Post-Training: A Deep Dive into Reasoning Large Language Models [131.10969986056]
  Large Language Models (LLMs) have transformed the natural language processing landscape and brought to life diverse applications.<n>Post-training methods enable LLMs to refine their knowledge, improve reasoning, enhance factual accuracy, and align more effectively with user intents and ethical considerations.
  arXiv  Detail & Related papers  (2025-02-28T18:59:54Z)
• LoRE-Merging: Exploring Low-Rank Estimation For Large Language Model Merging [10.33844295243509]
  We propose a unified framework for model merging based on low-rank estimation of task vectors without the need for access to the base model, named textscLoRE-Merging.<n>Our approach is motivated by the observation that task vectors from fine-tuned models frequently exhibit a limited number of dominant singular values, making low-rank estimations less prone to interference.
  arXiv  Detail & Related papers  (2025-02-15T10:18:46Z)
• ChameleonLLM: Batch-Aware Dynamic Low-Rank Adaptation via Inference-Time Clusters [3.729242965449096]
  This paper introduces ChameleonLLM, a novel framework that enables inference-time adaptation of large language models.<n>Unlike traditional fine-tuning approaches such as Low-Rank Adaptation (LoRA), our method dynamically generates adaptive modifications to the decoder weights.<n>By intelligently grouping similar inputs and computing context-aware low-rank updates via a hyper-network, ChameleonLLM achieves significant performance gains.
  arXiv  Detail & Related papers  (2025-02-06T18:57:06Z)
• First-Passage Approach to Optimizing Perturbations for Improved Training of Machine Learning Models [0.0]
  We frame machine learning protocols as first-passage processes and consider their response to perturbations.<n>We show that if the unperturbed learning process reaches a quasi-steady state, the response at a single perturbation frequency can predict the behavior at a wide range of frequencies.
  arXiv  Detail & Related papers  (2025-02-06T14:53:21Z)
• 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)

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.