IFDID: Information Filter upon Diversity-Improved Decoding for Diversity-Faithfulness Tradeoff in NLG

• URL: http://arxiv.org/abs/2210.13829v3
• Date: Thu, 9 May 2024 12:28:04 GMT
• Title: IFDID: Information Filter upon Diversity-Improved Decoding for Diversity-Faithfulness Tradeoff in NLG
• Authors: Han Meng, Xiaosong He, Zexing Chen, Feng Zhou,
• Abstract summary: 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.
• Score: 5.771099867942164
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Some Natural Language Generation (NLG) tasks require both faithfulness and diversity. The decoding strategy is intensively related to the quality of the generated text. Strategies such as beam search, greedy search, etc., perform with low diversity and high repetition. On the other hand, guided decoding, the solution towards diversity, may generate unfaithful expressions. To this end, this paper presents Information Filter upon Diversity-Improved Decoding (IFDID) to obtain the tradeoff between diversity and faithfulness. IFDID is a two-stage decoding strategy leveraging the proposed Enhance-Filter framework, which achieves the tradeoff by increasing the probabilities of some typical tokens being selected and subsequently filtering them by their information amount. To verify the effectiveness, we compare our method with other baselines on related CommonGEN, RocStories and AdGen benchmarks, which cover Chinese and English datasets. Our numerical experimental results and human evaluation outcomes verify the effectiveness of the proposed approach, as 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, demonstrating that IFDID is a novel SOTA decoding strategy for the tradeoff between diversity and faithfulness.

Related papers

• Semantic-guided Diverse Decoding for Large Language Model [13.808245335025308]
  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.
  arXiv  Detail & Related papers  (2025-06-30T08:06:49Z)
• 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)
• 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. Although preference-tuned models exhibit reduced lexical and syntactic diversity, they produce greater effective semantic diversity than SFT or base models. These findings have important implications for applications that require diverse yet high-quality outputs.
  arXiv  Detail & Related papers  (2025-04-16T23:02:23Z)
• DEUCE: Dual-diversity Enhancement and Uncertainty-awareness for Cold-start Active Learning [54.35107462768146]
  Cold-start active learning (CSAL) selects valuable instances from an unlabeled dataset for manual annotation. Existing CSAL methods overlook weak classes and hard representative examples, resulting in biased learning. This paper proposes a novel dual-diversity enhancing and uncertainty-aware framework for CSAL.
  arXiv  Detail & Related papers  (2025-02-01T04:00:03Z)
• Generative Retrieval Meets Multi-Graded Relevance [104.75244721442756]
  We introduce a framework called GRaded Generative Retrieval (GR$2$) GR$2$ focuses on two key components: ensuring relevant and distinct identifiers, and implementing multi-graded constrained contrastive training. Experiments on datasets with both multi-graded and binary relevance demonstrate the effectiveness of GR$2$.
  arXiv  Detail & Related papers  (2024-09-27T02:55:53Z)
• DiveR-CT: Diversity-enhanced Red Teaming with Relaxing Constraints [68.82294911302579]
  We introduce DiveR-CT, which relaxes conventional constraints on the objective and semantic reward, granting greater freedom for the policy to enhance diversity. Our experiments demonstrate DiveR-CT's marked superiority over baselines by 1) generating data that perform better in various diversity metrics across different attack success rate levels, 2) better-enhancing resiliency in blue team models through safety tuning based on collected data, 3) allowing dynamic control of objective weights for reliable and controllable attack success rates, and 4) reducing susceptibility to reward overoptimization.
  arXiv  Detail & Related papers  (2024-05-29T12:12:09Z)
• Learnable Item Tokenization for Generative Recommendation [78.30417863309061]
  We propose LETTER (a LEarnable Tokenizer for generaTivE Recommendation), which integrates hierarchical semantics, collaborative signals, and code assignment diversity. LETTER incorporates Residual Quantized VAE for semantic regularization, a contrastive alignment loss for collaborative regularization, and a diversity loss to mitigate code assignment bias.
  arXiv  Detail & Related papers  (2024-05-12T15:49:38Z)
• Fidelity-Enriched Contrastive Search: Reconciling the Faithfulness-Diversity Trade-Off in Text Generation [21.096737598952853]
  We propose a new decoding method called Fidelity-Enriched Contrastive Search (FECS) FECS promotes tokens that are semantically similar to the provided source while penalizing repetitiveness in the generated text. Results show that FECS consistently enhances faithfulness across various language model sizes while maintaining output diversity comparable to well-performing decoding algorithms.
  arXiv  Detail & Related papers  (2023-10-23T14:27:45Z)
• Towards General Visual-Linguistic Face Forgery Detection [95.73987327101143]
  Deepfakes are realistic face manipulations that can pose serious threats to security, privacy, and trust. Existing methods mostly treat this task as binary classification, which uses digital labels or mask signals to train the detection model. We propose a novel paradigm named Visual-Linguistic Face Forgery Detection(VLFFD), which uses fine-grained sentence-level prompts as the annotation.
  arXiv  Detail & Related papers  (2023-07-31T10:22:33Z)
• A Unified Algorithm Framework for Unsupervised Discovery of Skills based on Determinantal Point Process [53.86223883060367]
  We show that diversity and coverage in unsupervised option discovery can indeed be unified under the same mathematical framework. Our proposed algorithm, ODPP, has undergone extensive evaluation on challenging tasks created with Mujoco and Atari.
  arXiv  Detail & Related papers  (2022-12-01T01:40:03Z)
• Contrastive Identity-Aware Learning for Multi-Agent Value Decomposition [31.877237996738252]
  Value Decomposition (VD) aims to deduce the contributions of agents for decentralized policies in the presence of only global rewards. One of the main challenges in VD is to promote diverse behaviors among agents, while existing methods directly encourage the diversity of learned agent networks. We propose a novel Contrastive Identity-Aware learning (CIA) method, explicitly boosting the credit-level distinguishability of the VD network.
  arXiv  Detail & Related papers  (2022-11-23T05:18:42Z)
• A Closer Look at Few-shot Image Generation [38.83570296616384]
  When transferring pretrained GANs on small target data, the generator tends to replicate the training samples. Several methods have been proposed to address this few-shot image generation, but there is a lack of effort to analyze them under a unified framework. We propose a framework to analyze existing methods during the adaptation. Second contribution proposes to apply mutual information (MI) to retain the source domain's rich multi-level diversity information in the target domain generator.
  arXiv  Detail & Related papers  (2022-05-08T07:46:26Z)
• Diverse Text Generation via Variational Encoder-Decoder Models with Gaussian Process Priors [21.71928935339393]
  We present a novel latent structured variable model to generate high quality texts. Specifically, we introduce a function to map deterministic encoder hidden states into random context variables. To address the learning challenge of Gaussian processes, we propose an efficient variational inference approach.
  arXiv  Detail & Related papers  (2022-04-04T04:09:15Z)
• CoDA: Contrast-enhanced and Diversity-promoting Data Augmentation for Natural Language Understanding [67.61357003974153]
  We propose a novel data augmentation framework dubbed CoDA. CoDA synthesizes diverse and informative augmented examples by integrating multiple transformations organically. A contrastive regularization objective is introduced to capture the global relationship among all the data samples.
  arXiv  Detail & Related papers  (2020-10-16T23:57:03Z)
• Informed Sampling for Diversity in Concept-to-Text NLG [8.883733362171034]
  We propose an Imitation Learning approach to explore the level of diversity that a language generation model can reliably produce. Specifically, we augment the decoding process with a meta-classifier trained to distinguish which words at any given timestep will lead to high-quality output.
  arXiv  Detail & Related papers  (2020-04-29T17:43:24Z)

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.