QD-LLM evolves prompt embeddings via neuroevolution in a quality-diversity framework, delivering 46% higher coverage and 41% higher QD-score than prior methods on coding and writing benchmarks.
Contrastive Decoding: Open-ended Text Generation as Optimization
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
years
2026 5verdicts
UNVERDICTED 5representative citing papers
ESamp trains a test-time distiller to model LLM depth-wise representation transitions and biases decoding toward high prediction-error paths to increase semantic diversity.
TriMix dynamically fuses logits from three model sources to outperform baselines and Proxy Tuning on eight low-resource languages across four model families.
Probabilistic circuits detect LLM hallucinations as residual-stream anomalies with up to 99% AUROC and enable dynamic correction that raises truthfulness scores while cutting unnecessary output corruption.
LightEdit enables scalable lifelong knowledge editing in LLMs via selective knowledge retrieval and probability suppression during decoding, outperforming prior methods on ZSRE, Counterfact, and RIPE while reducing training costs.
citing papers explorer
-
Parameter-Efficient Neuroevolution for Diverse LLM Generation: Quality-Diversity Optimization via Prompt Embedding Evolution
QD-LLM evolves prompt embeddings via neuroevolution in a quality-diversity framework, delivering 46% higher coverage and 41% higher QD-score than prior methods on coding and writing benchmarks.
-
Large Language Models Explore by Latent Distilling
ESamp trains a test-time distiller to model LLM depth-wise representation transitions and biases decoding toward high prediction-error paths to increase semantic diversity.
-
Efficient Low-Resource Language Adaptation via Multi-Source Dynamic Logit Fusion
TriMix dynamically fuses logits from three model sources to outperform baselines and Proxy Tuning on eight low-resource languages across four model families.
-
Hallucination as an Anomaly: Dynamic Intervention via Probabilistic Circuits
Probabilistic circuits detect LLM hallucinations as residual-stream anomalies with up to 99% AUROC and enable dynamic correction that raises truthfulness scores while cutting unnecessary output corruption.
-
Towards Scalable Lifelong Knowledge Editing with Selective Knowledge Suppression
LightEdit enables scalable lifelong knowledge editing in LLMs via selective knowledge retrieval and probability suppression during decoding, outperforming prior methods on ZSRE, Counterfact, and RIPE while reducing training costs.