相关论文: Post-Training Language Models for Crosslingual Con…

Language model (LM) post-training (or alignment) involves maximizing a reward function that is derived from preference annotations. Direct Preference Optimization (DPO) is a popular offline alignment method that trains a policy directly on…

Discourse coherence plays an important role in the translation of one text. However, the previous reported models most focus on improving performance over individual sentence while ignoring cross-sentence links and dependencies, which…

To adapt large language models (LLMs) to ranking tasks, existing list-wise methods, represented by list-wise Direct Preference Optimization (DPO), focus on optimizing partial-order or full-order list ranking consistency for LLMs to enhance…

Although Large Language Models (LLMs) have made remarkable progress, current preference optimization methods still struggle to align directional consistency while preserving reasoning diversity. To address this limitation, we propose…

We study the problem of multilingual masked language modeling, i.e. the training of a single model on concatenated text from multiple languages, and present a detailed study of several factors that influence why these models are so…

Large language models (LLMs) require careful alignment to balance competing objectives - factuality, safety, conciseness, proactivity, and diversity. Existing studies focus on individual techniques or specific dimensions, lacking a holistic…

Traditional language model alignment methods, such as Direct Preference Optimization (DPO), are limited by their dependence on static, pre-collected paired preference data, which hampers their adaptability and practical applicability. To…

Alignment is a crucial step to enhance the instruction-following and conversational abilities of language models. Despite many recent work proposing new algorithms, datasets, and training pipelines, there is a lack of comprehensive studies…

Recent advances in preference optimization have demonstrated significant potential for improving mathematical reasoning capabilities in large language models (LLMs). While current approaches leverage high-quality pairwise preference data…

Reinforcement learning with verifiable reward (RLVR) has been instrumental in eliciting strong reasoning capabilities from large language models (LLMs) via long chains of thought (CoT). During RLVR training, we formalize and systemically…

The rapid rise of large language models (LLMs) has unlocked many applications but also underscores the challenge of aligning them with diverse values and preferences. Direct Preference Optimization (DPO) is central to alignment but…

Recently, fine-tuning pre-trained language models (e.g., multilingual BERT) to downstream cross-lingual tasks has shown promising results. However, the fine-tuning process inevitably changes the parameters of the pre-trained model and…

Advances in neural modeling have achieved state-of-the-art (SOTA) results on public natural language processing (NLP) benchmarks, at times surpassing human performance. However, there is a gap between public benchmarks and real-world…

Large language models (LLMs) provide detailed and impressive responses to queries in English. However, are they really consistent at responding to the same query in other languages? The popular way of evaluating for multilingual performance…

Despite strong performance on a variety of tasks, neural sequence models trained with maximum likelihood have been shown to exhibit issues such as length bias and degenerate repetition. We study the related issue of receiving…

Post-training of language models, either through reinforcement learning, preference optimization or supervised finetuning, tends to sharpen the output probability distribution and reduce the diversity of generated responses. This is…

Direct Preference Optimization (DPO) improves the alignment of large language models (LLMs) with human values by training directly on human preference datasets, eliminating the need for reward models. However, due to the presence of…

Cross-lingual alignment (CLA) aims to align multilingual representations, enabling Large Language Models (LLMs) to seamlessly transfer knowledge across languages. While intuitive, we hypothesize, this pursuit of representational convergence…

Post-training plays a crucial role in refining and aligning large language models to meet specific tasks and human preferences. While recent advancements in post-training techniques, such as Group Relative Policy Optimization (GRPO),…

Current language model training paradigms typically terminate learning upon reaching the end-of-sequence (<eos>) token, overlooking the potential learning opportunities in the post-completion space. We propose Post-Completion Learning…