#decoding-strategy News & Analysis

5 articles tagged with #decoding-strategy. AI-curated summaries with sentiment analysis and key takeaways from 50+ sources.

5 articles

AIBullisharXiv – CS AI · May 127/10

🧠

Entropy-informed Decoding: Adaptive Information-Driven Branching

Researchers introduce Entropy-informed Decoding (EDEN), a novel framework that optimizes how large language models generate text by dynamically adjusting computational effort based on output uncertainty. The method matches or exceeds the performance of traditional beam search while using fewer computational expansions, particularly improving results on complex tasks like mathematical reasoning and code generation.

AIBullisharXiv – CS AI · Mar 46/103

🧠

Self-Aug: Query and Entropy Adaptive Decoding for Large Vision-Language Models

Researchers developed a new training-free decoding strategy for Large Vision-Language Models that reduces hallucinations by using query-adaptive visual augmentation and entropy-based token selection. The method showed significant improvements in factual consistency across four LVLMs and seven benchmarks compared to existing approaches.

AINeutralarXiv – CS AI · May 296/10

🧠

The Confidence Shortcut: A Reasoning Failure Mode of Masked Diffusion Models

Researchers identify a critical failure mode in masked diffusion language models where confidence-based decoding strategies cause reasoning errors on complex tasks. The study demonstrates that confidence-aligned training amplifies these failures by an order of magnitude, while random masking preserves robust reasoning capabilities across five reasoning tasks.

AINeutralarXiv – CS AI · May 286/10

🧠

Diffusion Large Language Models for Visual Speech Recognition

Researchers introduce DLLM-VSR, a diffusion-based large language model framework for visual speech recognition that replaces traditional left-to-right decoding with iterative masked denoising. The system achieves state-of-the-art 19.5% word error rate on LRS3 by using confidence-based unmasking and length-guided candidate decoding to resolve visual ambiguities.

AIBullisharXiv – CS AI · Mar 176/10

🧠

Thinking in Uncertainty: Mitigating Hallucinations in MLRMs with Latent Entropy-Aware Decoding

Researchers propose Latent Entropy-Aware Decoding (LEAD), a new method to reduce hallucinations in multimodal large reasoning models by switching between continuous and discrete token embeddings based on entropy states. The technique addresses issues where transition words correlate with high-entropy states that lead to unreliable outputs in visual question answering tasks.