Maximizing joint conditional mutual information I(Y; C_Z, W, Z | X) decomposes multi-objective LLM alignment into preference-specific DPO terms plus an I(Y;W|X) exploration term that reduces reward-distribution overlap.
arXiv preprint arXiv:2401.03804 , year=
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
representative citing papers
RCA is a training-free module that boosts input context signal strength in the residual stream of LLMs by orthogonal decoupling of attention routing from value magnitude.
Twin-Pass Chain-of-Thought Ensembling cuts Expected Calibration Error by up to 88% in Gemma-3 models on TeleQnA, ORANBench, and srsRANBench.
DCO is an inference-time intervention that decomposes attention head outputs orthogonally to a dynamic context anchor and suppresses outlier components via Z-score to improve contextual faithfulness in Llama models.
SMCS coordinates 15 open-source LLMs via retrieval-based prior selection and exploration-exploitation posterior enhancement, outperforming GPT-4.1 by 5.36% and GPT-o3-mini by 5.28% on eight benchmarks.
LlamaFactory provides a unified no-code framework for efficient fine-tuning of 100+ LLMs via an integrated web UI and has been released on GitHub.
citing papers explorer
-
Multi-Objective Exploration and Preference Optimization via Mutual Information
Maximizing joint conditional mutual information I(Y; C_Z, W, Z | X) decomposes multi-objective LLM alignment into preference-specific DPO terms plus an I(Y;W|X) exploration term that reduces reward-distribution overlap.
-
Resonant Context Anchoring: Decoupling Attention Routing and Signal Gain at Inference Time
RCA is a training-free module that boosts input context signal strength in the residual stream of LLMs by orthogonal decoupling of attention routing from value magnitude.
-
Enhancing Confidence Estimation in Telco LLMs via Twin-Pass CoT-Ensembling
Twin-Pass Chain-of-Thought Ensembling cuts Expected Calibration Error by up to 88% in Gemma-3 models on TeleQnA, ORANBench, and srsRANBench.
-
Hallucinations as Orthogonal Noise: Inference-Time Manifold Alignment via Dynamic Contextual Orthogonalization
DCO is an inference-time intervention that decomposes attention head outputs orthogonally to a dynamic context anchor and suppresses outlier components via Z-score to improve contextual faithfulness in Llama models.
-
A Scalable Multi-LLM Collaboration System with Retrieval-based Selection and Exploration-Exploitation-Driven Enhancement
SMCS coordinates 15 open-source LLMs via retrieval-based prior selection and exploration-exploitation posterior enhancement, outperforming GPT-4.1 by 5.36% and GPT-o3-mini by 5.28% on eight benchmarks.
-
LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Models
LlamaFactory provides a unified no-code framework for efficient fine-tuning of 100+ LLMs via an integrated web UI and has been released on GitHub.