Semantic-guided Diverse Decoding for Large Language Model

• URL: http://arxiv.org/abs/2506.23601v1
• Date: Mon, 30 Jun 2025 08:06:49 GMT
• Title: Semantic-guided Diverse Decoding for Large Language Model
• Authors: Weijie Shi, Yue Cui, Yaguang Wu, Jingzhi Fang, Shibo Zhang, Mengze Li, Sirui Han, Jia Zhu, Jiajie Xu, Xiaofang Zhou,
• Abstract summary: We introduce Semantic-guided Diverse Decoding (SemDiD)<n>SemDiD balances quality with diversity through three complementary mechanisms: directional guidance, dynamic inter-group repulsion, and position-debiased probability assessment.<n>Experiments show SemDiD consistently outperforms existing methods.
• Score: 13.808245335025308
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: Diverse decoding of large language models is crucial for applications requiring multiple semantically distinct responses, yet existing methods primarily achieve lexical rather than semantic diversity. This limitation significantly constrains Best-of-N strategies, group-based reinforcement learning, and data synthesis. While temperature sampling and diverse beam search modify token distributions or apply n-gram penalties, they fail to ensure meaningful semantic differentiation. We introduce Semantic-guided Diverse Decoding (SemDiD), operating directly in embedding space that balances quality with diversity through three complementary mechanisms: orthogonal directional guidance, dynamic inter-group repulsion, and position-debiased probability assessment. SemDiD harmonizes these competing objectives using adaptive gain functions and constraint optimization, ensuring both quality thresholds and maximal semantic differentiation. Experiments show SemDiD consistently outperforms existing methods, improving Best-of-N coverage by 1.4-5.2% across diverse tasks and accelerating RLHF training convergence by 15% while increasing accuracy by up to 2.1%.

Related papers

• Semantic uncertainty in advanced decoding methods for LLM generation [35.31962554915952]
  This study investigates semantic uncertainty in large language model (LLM) outputs across different decoding methods.<n>We analyze how different decoding strategies affect both the diversity and reliability of model outputs.
  arXiv  Detail & Related papers  (2025-06-17T10:09:29Z)
• Multi-Level Aware Preference Learning: Enhancing RLHF for Complex Multi-Instruction Tasks [81.44256822500257]
  RLHF has emerged as a predominant approach for aligning artificial intelligence systems with human preferences.<n> RLHF exhibits insufficient compliance capabilities when confronted with complex multi-instruction tasks.<n>We propose a novel Multi-level Aware Preference Learning (MAPL) framework, capable of enhancing multi-instruction capabilities.
  arXiv  Detail & Related papers  (2025-05-19T08:33:11Z)
• Evaluating the Diversity and Quality of LLM Generated Content [72.84945252821908]
  We introduce a framework for measuring effective semantic diversity--diversity among outputs that meet quality thresholds.<n>Although preference-tuned models exhibit reduced lexical and syntactic diversity, they produce greater effective semantic diversity than SFT or base models.<n>These findings have important implications for applications that require diverse yet high-quality outputs.
  arXiv  Detail & Related papers  (2025-04-16T23:02:23Z)
• IPSeg: Image Posterior Mitigates Semantic Drift in Class-Incremental Segmentation [77.06177202334398]
  We identify two critical challenges in CISS that contribute to semantic drift and degrade performance.<n>First, we highlight the issue of separate optimization, where different parts of the model are optimized in distinct incremental stages.<n>Second, we identify noisy semantics arising from inappropriate pseudo-labeling, which results in sub-optimal results.
  arXiv  Detail & Related papers  (2025-02-07T12:19:37Z)
• Phasic Diversity Optimization for Population-Based Reinforcement Learning [10.15130620537703]
  Phasic Diversity Optimization (PDO) algorithm separates reward and diversity training into distinct phases. In the auxiliary phase, agents with poor performance diversified via determinants will not replace the better agents in the archive. We introduce two implementations of PDO archive and conduct tests in the newly proposed adversarial dogfight and MuJoCo simulations.
  arXiv  Detail & Related papers  (2024-03-17T06:41:09Z)
• Object Segmentation by Mining Cross-Modal Semantics [68.88086621181628]
  We propose a novel approach by mining the Cross-Modal Semantics to guide the fusion and decoding of multimodal features. Specifically, we propose a novel network, termed XMSNet, consisting of (1) all-round attentive fusion (AF), (2) coarse-to-fine decoder (CFD), and (3) cross-layer self-supervision.
  arXiv  Detail & Related papers  (2023-05-17T14:30:11Z)
• Exact Subspace Diffusion for Decentralized Multitask Learning [17.592204922442832]
  Distributed strategies for multitask learning induce relationships between agents in a more nuanced manner, and encourage collaboration without enforcing consensus. We develop a generalization of the exact diffusion algorithm for subspace constrained multitask learning over networks, and derive an accurate expression for its mean-squared deviation. We verify numerically the accuracy of the predicted performance expressions, as well as the improved performance of the proposed approach over alternatives based on approximate projections.
  arXiv  Detail & Related papers  (2023-04-14T19:42:19Z)
• IFDID: Information Filter upon Diversity-Improved Decoding for Diversity-Faithfulness Tradeoff in NLG [5.771099867942164]
  This paper presents Information Filter upon Diversity-Improved Decoding (IFDID) to obtain the tradeoff between diversity and faithfulness. Our approach achieves a 1.24 higher ROUGE score describing faithfulness as well as higher diversity represented by 62.5% higher upon Dist-2 than traditional approaches.
  arXiv  Detail & Related papers  (2022-10-25T08:14:20Z)
• Consistency and Diversity induced Human Motion Segmentation [231.36289425663702]
  We propose a novel Consistency and Diversity induced human Motion (CDMS) algorithm. Our model factorizes the source and target data into distinct multi-layer feature spaces. A multi-mutual learning strategy is carried out to reduce the domain gap between the source and target data.
  arXiv  Detail & Related papers  (2022-02-10T06:23:56Z)
• Semi-supervised Domain Adaptive Structure Learning [72.01544419893628]
  Semi-supervised domain adaptation (SSDA) is a challenging problem requiring methods to overcome both 1) overfitting towards poorly annotated data and 2) distribution shift across domains. We introduce an adaptive structure learning method to regularize the cooperation of SSL and DA.
  arXiv  Detail & Related papers  (2021-12-12T06:11:16Z)

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.