Inference-Time Language Model Alignment via Integrated Value Guidance

• URL: http://arxiv.org/abs/2409.17819v1
• Date: Thu, 26 Sep 2024 13:15:18 GMT
• Title: Inference-Time Language Model Alignment via Integrated Value Guidance
• Authors: Zhixuan Liu, Zhanhui Zhou, Yuanfu Wang, Chao Yang, Yu Qiao,
• Abstract summary: We introduce $textitIntegrated Value Guidance$ (IVG) IVG uses implicit and explicit value functions to guide language model decoding at token and chunk-level. We demonstrate IVG's versatility across various tasks.
• Score: 21.294207620111525
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large language models are typically fine-tuned to align with human preferences, but tuning large models is computationally intensive and complex. In this work, we introduce $\textit{Integrated Value Guidance}$ (IVG), a method that uses implicit and explicit value functions to guide language model decoding at token and chunk-level respectively, efficiently aligning large language models purely at inference time. This approach circumvents the complexities of direct fine-tuning and outperforms traditional methods. Empirically, we demonstrate the versatility of IVG across various tasks. In controlled sentiment generation and summarization tasks, our method significantly improves the alignment of large models using inference-time guidance from $\texttt{gpt2}$-based value functions. Moreover, in a more challenging instruction-following benchmark AlpacaEval 2.0, we show that both specifically tuned and off-the-shelf value functions greatly improve the length-controlled win rates of large models against $\texttt{gpt-4-turbo}$ (e.g., $19.51\% \rightarrow 26.51\%$ for $\texttt{Mistral-7B-Instruct-v0.2}$ and $25.58\% \rightarrow 33.75\%$ for $\texttt{Mixtral-8x7B-Instruct-v0.1}$ with Tulu guidance).

Related papers

• NeKo: Toward Post Recognition Generative Correction Large Language Models with Task-Oriented Experts [57.53692236201343]
  We propose a Multi-Task Correction MoE, where we train the experts to become an expert'' of speech-to-text, language-to-text and vision-to-text datasets. NeKo performs competitively on grammar and post-OCR correction as a multi-task model.
  arXiv  Detail & Related papers  (2024-11-08T20:11:24Z)
• Transfer Q Star: Principled Decoding for LLM Alignment [105.89114186982972]
  Transfer $Q*$ estimates the optimal value function for a target reward $r$ through a baseline model. Our approach significantly reduces the sub-optimality gap observed in prior SoTA methods.
  arXiv  Detail & Related papers  (2024-05-30T21:36:12Z)
• Weak-to-Strong Search: Align Large Language Models via Searching over Small Language Models [22.425339110551743]
  We introduce $textitweak-to-strong search, framing the alignment of a large language model as a test-time greedy search. In controlled-sentiment generation and summarization, we use tuned and untuned $textttgpt2$s to improve the alignment of large models without additional training. In a more difficult instruction-following benchmark, we show that reusing off-the-shelf small models can improve the length-controlled win rates of both white-box and black-box large models.
  arXiv  Detail & Related papers  (2024-05-29T16:55:32Z)
• On the Role of Bidirectionality in Language Model Pre-Training [85.14614350372004]
  We study the role of bidirectionality in next token prediction, text infilling, zero-shot priming and fine-tuning. We train models with up to 6.7B parameters, and find differences to remain consistent at scale.
  arXiv  Detail & Related papers  (2022-05-24T02:25:05Z)
• $\mathcal{Y}$-Tuning: An Efficient Tuning Paradigm for Large-Scale Pre-Trained Models via Label Representation Learning [47.742220473129684]
  $mathcalY$-tuning learns dense representations for labels defined in a given task and aligns them to fixed feature representation. For $textDeBERTa_textXXL$ with 1.6 billion parameters, $mathcalY$-tuning achieves performance more than $96%$ of full fine-tuning on GLUE Benchmark.
  arXiv  Detail & Related papers  (2022-02-20T13:49:34Z)
• CoreLM: Coreference-aware Language Model Fine-Tuning [0.0]
  We propose a Fine-Tuning framework, named CoreLM, that extends the architecture of current Pretrained Language Models. We make available information outside the contextual space of the model, which results in a better Language Model for a fraction of the computational cost. Our proposed model achieves a lower Perplexity in GUMBY and LAMBDADA datasets when compared to GPT2 and a fine-tuned version of GPT2 without any changes.
  arXiv  Detail & Related papers  (2021-11-04T08:44:31Z)
• Improving Robustness and Generality of NLP Models Using Disentangled Representations [62.08794500431367]
  Supervised neural networks first map an input $x$ to a single representation $z$, and then map $z$ to the output label $y$. We present methods to improve robustness and generality of NLP models from the standpoint of disentangled representation learning. We show that models trained with the proposed criteria provide better robustness and domain adaptation ability in a wide range of supervised learning tasks.
  arXiv  Detail & Related papers  (2020-09-21T02:48:46Z)
• LAVA NAT: A Non-Autoregressive Translation Model with Look-Around Decoding and Vocabulary Attention [54.18121922040521]
  Non-autoregressive translation (NAT) models generate multiple tokens in one forward pass. These NAT models often suffer from the multimodality problem, generating duplicated tokens or missing tokens. We propose two novel methods to address this issue, the Look-Around (LA) strategy and the Vocabulary Attention (VA) mechanism.
  arXiv  Detail & Related papers  (2020-02-08T04:11:03Z)

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.