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

Current large language models (LLMs) generally show a significant performance gap in alignment between English and other languages. To bridge this gap, existing research typically leverages the model's responses in English as a reference to…

Direct alignment methods typically train large language models (LLMs) by contrasting the likelihoods of preferred and dispreferred responses. While effective at capturing relative preferences, these methods are widely observed to suppress…

Adapting large language models to other languages typically employs supervised fine-tuning (SFT) as a standard approach. However, it often suffers from an overemphasis on English performance, a phenomenon that is especially pronounced in…

Though reasoning abilities are considered language-agnostic, existing LLMs exhibit inconsistent reasoning abilities across different languages, e.g., reasoning in the dominant language like English is superior to other languages due to the…

In real-world services such as ChatGPT, aligning models based on user feedback is crucial for improving model performance. However, due to the simplicity and convenience of providing feedback, users typically offer only basic binary…

Cross-lingual alignment, the meaningful similarity of representations across languages in multilingual language models, has been an active field of research in recent years. We survey the literature of techniques to improve cross-lingual…

While multimodal large language models excel at tasks that integrate visual perception with symbolic reasoning, their performance is often undermined by a critical vulnerability: perception-induced errors that propagate through the…

Direct alignment algorithms have proven an effective step for aligning language models to human-desired behaviors. Current variants of the Direct Preference Optimization objective have focused on a strict setting where all tokens are…

Word alignment which aims to extract lexicon translation equivalents between source and target sentences, serves as a fundamental tool for natural language processing. Recent studies in this area have yielded substantial improvements by…

Language model calibration refers to the alignment between the confidence of the model and the actual performance of its responses. While previous studies point out the overconfidence phenomenon in Large Language Models (LLMs) and show that…

Contrastive learning models have demonstrated impressive abilities to capture semantic similarities by aligning representations in the embedding space. However, their performance can be limited by the quality of the training data and its…

While alignment algorithms are now commonly used to tune pre-trained language models towards a user's preferences, we lack explanations for the underlying mechanisms in which models become ``aligned'', thus making it difficult to explain…

The alignment of large language models with human values presents a critical challenge, particularly when balancing conflicting objectives like helpfulness and harmlessness. Existing approaches, such as Reinforcement Learning from Human…

Pre-trained language models (PrLMs) have achieved great success on a wide range of natural language processing tasks by virtue of the universal language representation ability obtained by self-supervised learning on a large corpus. These…

Multilingual generative models obtain remarkable cross-lingual in-context learning capabilities through pre-training on large-scale corpora. However, they still exhibit a performance bias toward high-resource languages and learn isolated…

We propose a post-training method for lower-resource languages that preserves the fluency of language models even when aligned by disfluent reward models. Preference optimization is now a well-researched topic, but previous work has mostly…

Direct Preference Optimization (DPO) has emerged as a de-facto approach for aligning language models with human preferences. Recent work has shown DPO's effectiveness relies on training data quality. In particular, clear quality differences…

Despite the widespread multilingual deployment of large language models, post-training pipelines remain predominantly English-centric, contributing to performance disparities across languages. We present a systematic, controlled study of…

Multilinguality is crucial for extending recent advancements in language modelling to diverse linguistic communities. To maintain high performance while representing multiple languages, multilingual models ideally align representations,…

Automatic prompt optimization (APO) has driven significant gains in LLM-based agentic workflows. However, existing methods treat each task's prompt as a monolithic, instance-blind string optimized through global edits, producing brittle…