Inference time LLM alignment in single and multidomain preference spectrum

• URL: http://arxiv.org/abs/2410.19206v1
• Date: Thu, 24 Oct 2024 23:31:39 GMT
• Title: Inference time LLM alignment in single and multidomain preference spectrum
• Authors: Sadat Shahriar, Zheng Qi, Nikolaos Pappas, Srikanth Doss, Monica Sunkara, Kishaloy Halder, Manuel Mager, Yassine Benajiba,
• Abstract summary: We introduce inference-time model alignment method that learns encoded representations of preference dimensions. These representations are computed by subtraction of the base model from the aligned model as in model editing. Even though the preference dimensions can span various levels, here we focus on three gradual response levels across three specialized domains.
• Score: 16.849200702288307
• License:
• Abstract: Aligning Large Language Models (LLM) to address subjectivity and nuanced preference levels requires adequate flexibility and control, which can be a resource-intensive and time-consuming procedure. Existing training-time alignment methods require full re-training when a change is needed and inference-time ones typically require access to the reward model at each inference step. To address these limitations, we introduce inference-time model alignment method that learns encoded representations of preference dimensions, called \textit{Alignment Vectors} (AV). These representations are computed by subtraction of the base model from the aligned model as in model editing enabling dynamically adjusting the model behavior during inference through simple linear operations. Even though the preference dimensions can span various granularity levels, here we focus on three gradual response levels across three specialized domains: medical, legal, and financial, exemplifying its practical potential. This new alignment paradigm introduces adjustable preference knobs during inference, allowing users to tailor their LLM outputs while reducing the inference cost by half compared to the prompt engineering approach. Additionally, we find that AVs are transferable across different fine-tuning stages of the same model, demonstrating their flexibility. AVs also facilitate multidomain, diverse preference alignment, making the process 12x faster than the retraining approach.

Related papers

• Training Deep Learning Models with Norm-Constrained LMOs [56.00317694850397]
  We study optimization methods that leverage the linear minimization oracle (LMO) over a norm-ball. We propose a new family of algorithms that uses the LMO to adapt to the geometry of the problem and, perhaps surprisingly, show that they can be applied to unconstrained problems.
  arXiv  Detail & Related papers  (2025-02-11T13:10:34Z)
• Few-shot Steerable Alignment: Adapting Rewards and LLM Policies with Neural Processes [50.544186914115045]
  Large language models (LLMs) are increasingly embedded in everyday applications. Ensuring their alignment with the diverse preferences of individual users has become a critical challenge. We present a novel framework for few-shot steerable alignment.
  arXiv  Detail & Related papers  (2024-12-18T16:14:59Z)
• PAD: Personalized Alignment of LLMs at Decoding-Time [10.347782385286582]
  This paper presents a novel framework designed to align LLM outputs with diverse personalized preferences during the inference phase. The Personalized Alignment at Decoding-time (PAD) framework decouples the text generation process from personalized preferences. PAD not only outperforms existing training-based alignment methods in terms of aligning with diverse preferences but also shows significant generalizability to preferences unseen during training.
  arXiv  Detail & Related papers  (2024-10-05T08:00:55Z)
• 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)
• Flextron: Many-in-One Flexible Large Language Model [85.93260172698398]
  We introduce Flextron, a network architecture and post-training model optimization framework supporting flexible model deployment. We present a sample-efficient training method and associated routing algorithms for transforming an existing trained LLM into a Flextron model. We demonstrate superior performance over multiple end-to-end trained variants and other state-of-the-art elastic networks, all with a single pretraining run that consumes a mere 7.63% tokens compared to original pretraining.
  arXiv  Detail & Related papers  (2024-06-11T01:16:10Z)
• Rewards-in-Context: Multi-objective Alignment of Foundation Models with Dynamic Preference Adjustment [46.44464839353993]
  We introduce Rewards-in-Context (RiC), which conditions the response of a foundation model on multiple rewards in its prompt context. RiC only requires supervised fine-tuning of a single foundation model and supports dynamic adjustment for user preferences during inference time.
  arXiv  Detail & Related papers  (2024-02-15T18:58:31Z)
• Decoding-time Realignment of Language Models [44.54462397717971]
  We propose a simple method to explore and evaluate different regularization strengths in aligned models without retraining. DeRa enables control over the degree of alignment, allowing users to smoothly transition between unaligned and aligned models.
  arXiv  Detail & Related papers  (2024-02-05T13:31:28Z)
• TACTiS-2: Better, Faster, Simpler Attentional Copulas for Multivariate Time Series [57.4208255711412]
  Building on copula theory, we propose a simplified objective for the recently-introduced transformer-based attentional copulas (TACTiS) We show that the resulting model has significantly better training dynamics and achieves state-of-the-art performance across diverse real-world forecasting tasks.
  arXiv  Detail & Related papers  (2023-10-02T16:45:19Z)
• Gradient-Regulated Meta-Prompt Learning for Generalizable Vision-Language Models [137.74524357614285]
  We introduce a novel Gradient-RegulAted Meta-prompt learning framework. It helps pre-training models adapt to downstream tasks in a parameter -- and data -- efficient way. GRAM can be easily incorporated into various prompt tuning methods in a model-agnostic way.
  arXiv  Detail & Related papers  (2023-03-12T05:03:37Z)
• Model-agnostic and Scalable Counterfactual Explanations via Reinforcement Learning [0.5729426778193398]
  We propose a deep reinforcement learning approach that transforms the optimization procedure into an end-to-end learnable process. Our experiments on real-world data show that our method is model-agnostic, relying only on feedback from model predictions.
  arXiv  Detail & Related papers  (2021-06-04T16:54:36Z)

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.