mlsanityData to 14 Oct 2026

Improving Open-Ended Text Generation via Adaptive Decoding

arXiv 2402.18223 ↗First posted 28 Feb 2024cs.CLcited by 21

Not on the map. Why?

Abstract (arXiv)

Current language models decode text token by token according to probabilistic distribution, and determining the appropriate candidates for the next token is crucial to ensure generation quality. This study introduces adaptive decoding, a mechanism that dynamically empowers language models to ascertain a sensible candidate set during generation. Specifically, we introduce an entropy-based metric called confidence and conceptualize determining the optimal candidate set as a confidence-increasing process. The rationality of including a token in the candidate set is assessed by leveraging the increment of confidence. Experimental results reveal that our method balances diversity and coherence well. The human evaluation shows that our method can generate human-preferred text. Additionally, our method can potentially improve the reasoning ability of language models.

Key facts. Cited by 21 papers in the map (data through 14 Oct 2026). Builds on 21 of its 26 references that are in the map. First posted on arXiv 28 Feb 2024.

Builds on

21 of 26 references.

References · 21

  1. 2020Language Models are Few-Shot Learnerscited by 32,419
  2. 2021Training Verifiers to Solve Math Word Problemscited by 10,109
  3. 2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arenacited by 8,626
  4. 2016Pointer Sentinel Mixture Modelscited by 3,096
  5. 2019The Curious Case of Neural Text Degenerationcited by 2,916
  6. 2021SimCSE: Simple Contrastive Learning of Sentence Embeddingscited by 2,173
  7. 2018Hierarchical Neural Story Generationcited by 1,193
  8. 2020Beyond Accuracy: Behavioral Testing of NLP models with CheckListcited by 1,006
  9. 2019Neural Text Generation with Unlikelihood Trainingcited by 503
  10. 2021MAUVE: Measuring the Gap Between Neural Text and Human Text using Divergence Frontierscited by 470
  11. 2016A Corpus and Evaluation Framework for Deeper Understanding of Commonsense Storiescited by 417
  12. 2022A Contrastive Framework for Neural Text Generationcited by 225
9 more
  1. 2022Truncation Sampling as Language Model Desmoothingcited by 123
  2. 2022Locally Typical Samplingcited by 111
  3. 2019Don't Say That! Making Inconsistent Dialogue Unlikely with Unlikelihood Trainingcited by 110
  4. 2022Learning to Break the Loop: Analyzing and Mitigating Repetitions for Neural Text Generationcited by 94
  5. 2023Closing the Curious Case of Neural Text Degenerationcited by 32
  6. 2023On the Efficacy of Sampling Adapterscited by 17
  7. 2023Penalty Decoding: Well Suppress the Self-Reinforcement Effect in Open-Ended Text Generationcited by 13
  8. 2023Look-back Decoding for Open-Ended Text Generationcited by 10
  9. 2023EMO: Earth Mover Distance Optimization for Auto-Regressive Language Modelingcited by 7

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 7; 2025: 9; 2026: 5.

21 papers.

Sort:

By area:

  1. 2024Turning Up the Heat: Min-p Sampling for Creative and Coherent LLM Outputscited by 150
  2. 2024Decoding Decoded: Understanding Hyperparameter Effects in Open-Ended Text Generationcited by 26
  3. 2024Weak-to-Strong Preference Optimization: Stealing Reward from Weak Aligned Modelcited by 22
  4. 2024Balancing Diversity and Risk in LLM Sampling: How to Select Your Method and Parameter for Open-Ended Text Generationcited by 19
  5. 2024Adaptive Decoding via Latent Preference Optimizationcited by 10
  6. 2025InvisibleInk: High-Utility and Low-Cost Text Generation with Differential Privacycited by 10
  7. 2025GUARD: Glocal Uncertainty-Aware Robust Decoding for Effective and Efficient Open-Ended Text Generationcited by 10
  8. 2026Min-k Sampling: Decoupling Truncation from Temperature Scaling via Relative Logit Dynamicscited by 9
  9. 2026Hybrid Policy Distillation for LLMscited by 9
  10. 2025Optimizing Decoding Paths in Masked Diffusion Models by Quantifying Uncertaintycited by 6
  11. 2025p-less Sampling: A Robust Hyperparameter-Free Approach for LLM Decodingcited by 5
  12. 2026A More Word-like Image Tokenization for MLLMscited by 3
9 more
  1. 2026Sampling More, Getting Less: Calibration is the Diversity Bottleneck in LLMscited by 2
  2. 2024ADLM -- stega: A Universal Adaptive Token Selection Algorithm for Improving Steganographic Text Quality via Information Entropycited by 1
  3. 2025On Next-Token Prediction in LLMs: How End Goals Determine the Consistency of Decoding Algorithmscited by 1
  4. 2025Short-Context Dominance: How Much Local Context Natural Language Actually Needs?cited by 1
  5. 2026Breaking the Likelihood Trap: Variance-Calibrated Modulation for Large Language Model Decodingcited by 1
  6. 2024First Place Solution of 2023 Global Artificial Intelligence Technology Innovation Competition Track 1cited by 0
  7. 2025Enhancing Learned Knowledge in LoRA Adapters Through Efficient Contrastive Decoding on Ascend NPUscited by 0
  8. 2025Unleashing the True Potential of LLMs: A Feedback-Triggered Self-Correction with Long-Term Multipath Decodingcited by 0
  9. 2025Auxiliary-Hyperparameter-Free Sampling: Entropy Equilibrium for Text Generationcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2022Confident Adaptive Language Modeling
  2. 2025Entropy Adaptive Decoding: Dynamic Model Switching for Efficient Inference
  3. 2026Entropy-informed Decoding: Adaptive Information-Driven Branching
  4. 2026Think Twice Before You Write -- an Entropy-based Decoding Strategy to Enhance LLM Reasoning
  5. 2025A Survey on Parallel Text Generation: From Parallel Decoding to Diffusion Language Models
  6. 2024AdaEDL: Early Draft Stopping for Speculative Decoding of Large Language Models via an Entropy-based Lower Bound on Token Acceptance Probability
  7. 2023Reward-Augmented Decoding: Efficient Controlled Text Generation With a Unidirectional Reward Model
  8. 2025Semantic uncertainty in advanced decoding methods for LLM generation