conftrace_

contrastive preference optimization

11 papers

Explore in graph

Also known as

CPO

Co-occurring keywords · papers mentioning both

large language model (5) neural machine translation (3) contrastive learning (2) parallel sentence (1) quantized low-rank adaptation (1) weak teacher (1) proof verification (1) proactive engagement (1) conditional reinforcement learning (1) quality estimator (1)

Papers

AMI at WMT25 General Translation Task: How Low Can We Go? Finetuning Lightweight Llama Models for Low Resource Machine Translation EMNLP 2025 Instruction-Tuned English to Bhojpuri Neural Machine Translation Using Contrastive Preference Optimization EMNLP 2025 Laniqo at WMT25 General Translation Task: Self-Improved and Retrieval-Augmented Translation EMNLP 2025 MACPO: Weak-to-Strong Alignment via Multi-Agent Contrastive Preference Optimization ICLR 2025 Sequence-level Large Language Model Training with Contrastive Preference Optimization NAACL 2025 Synthetic Proofs with Tool-Integrated Reasoning: Contrastive Alignment for LLM Mathematics with Lean EMNLP 2025 Contrastive Preference Optimization: Pushing the Boundaries of LLM Performance in Machine Translation ICML 2024 CUNI at WMT24 General Translation Task: LLMs, (Q)LoRA, CPO and Model Merging EMNLP 2024 Is Preference Alignment Always the Best Option to Enhance LLM-Based Translation? An Empirical Analysis EMNLP 2024 MACAROON: Training Vision-Language Models To Be Your Engaged Partners EMNLP 2024 SJTU System Description for the WMT24 Low-Resource Languages of Spain Task EMNLP 2024