conftrace_

decoding strategy

60 papers

Explore in graph

Co-occurring keywords

text generation (2913) large language model (13587) language model (4599) hallucination mitigation (320) beam search (309) neural machine translation (2310) nucleus sampling (26) text diversity (18) dialogue generation (454) factual accuracy (108)

Papers

𝜙-Decoding: Adaptive Foresight Sampling for Balanced Inference-Time Exploration and Exploitation ACL 2025
Uncertainty-Aware Contrastive Decoding ACL 2025
GUARD: Glocal Uncertainty-Aware Robust Decoding for Effective and Efficient Open-Ended Text Generation EMNLP 2025
SecDecoding: Steerable Decoding for Safer LLM Generation EMNLP 2025
Local Normalization Distortion and the Thermodynamic Formalism of Decoding Strategies for Large Language Models EMNLP 2025
Mitigating Sequential Dependencies: A Survey of Algorithms and Systems for Generation-Refinement Frameworks in Autoregressive Models EMNLP 2025
VASparse: Towards Efficient Visual Hallucination Mitigation via Visual-Aware Token Sparsification CVPR 2025
LLM can Achieve Self-Regulation via Hyperparameter Aware Generation ACL 2024
CleanGen: Mitigating Backdoor Attacks for Generation Tasks in Large Language Models EMNLP 2024
Adaptive Token Biaser: Knowledge Editing via Biasing Key Entities EMNLP 2024
Adaptive Contrastive Search: Uncertainty-Guided Decoding for Open-Ended Text Generation EMNLP 2024
Decoding Matters: Addressing Amplification Bias and Homogeneity Issue in Recommendations for Large Language Models EMNLP 2024
Synchronous Faithfulness Monitoring for Trustworthy Retrieval-Augmented Generation EMNLP 2024
SafeDecoding: Defending against Jailbreak Attacks via Safety-Aware Decoding ACL 2024
SLED: Self Logits Evolution Decoding for Improving Factuality in Large Language Models NIPS 2024
Outdated Issue Aware Decoding for Factual Knowledge Editing ACL 2024
Dynamic Stochastic Decoding Strategy for Open-Domain Dialogue Generation ACL 2024
On the alignment of LM language generation and human language comprehension EMNLP 2024
A Call for Clarity in Beam Search: How It Works and When It Stops COLING 2024
Hot or Cold? Adaptive Temperature Sampling for Code Generation with Large Language Models AAAI 2024
On Search Strategies for Document-Level Neural Machine Translation ACL 2023
Critic-Driven Decoding for Mitigating Hallucinations in Data-to-text Generation EMNLP 2023
Pointwise Mutual Information Based Metric and Decoding Strategy for Faithful Generation in Document Grounded Dialogs EMNLP 2023
Rethinking Model Selection and Decoding for Keyphrase Generation with Pre-trained Sequence-to-Sequence Models EMNLP 2023
Faithfulness-Aware Decoding Strategies for Abstractive Summarization EACL 2023