Related papers: Semi-Instruct: Bridging Natural-Instruct and Self-…
Large Language Models have become the de facto approach to sequence-to-sequence text generation tasks, but for specialized tasks/domains, a pretrained LLM lacks specific capabilities to produce accurate or well-formatted responses.…
Recently, Large Language Models (LLMs) have shown impressive language capabilities. While most of the existing LLMs have very unbalanced performance across different languages, multilingual alignment based on translation parallel data is an…
Instruction tuning as an effective technique aligns the outputs of large language models (LLMs) with human preference. But how to generate the seasonal multi-turn dialogues from raw documents for instruction tuning still requires further…
Instruction tuning has become essential for adapting large language models (LLMs) to follow domain-specific prompts. Yet, in specialized fields such as medicine, the scarcity of high-quality French instruction data limits effective…
Large language models (LLMs) are capable of performing conditional sequence generation tasks, such as translation or summarization, through instruction fine-tuning. The fine-tuning data is generally sequentially concatenated from a specific…
Motivation. Large language models (LLMs) have exhibited remarkable proficiency in diverse software engineering (SE) tasks. Handling such tasks typically involves acquiring foundational coding knowledge on large, general-purpose datasets…
Instruction tuning is critical to large language models (LLMs) for achieving better instruction following and task adaptation capabilities but its success heavily relies on the training data quality. Many recent methods focus on improving…
Self-training provides an effective means of using an extremely small amount of labeled data to create pseudo-labels for unlabeled data. Many state-of-the-art self-training approaches hinge on different regularization methods to prevent…
There is a growing trend of teaching large language models (LLMs) to solve mathematical problems through coding. Existing studies primarily focus on prompting powerful, closed-source models to generate seed training data followed by…
Although natural language instructions offer an intuitive way to guide automated image editing, deep-learning models often struggle to achieve high-quality results, largely due to the difficulty of creating large, high-quality training…
Instruction tuning is a crucial supervised training phase in Large Language Models (LLMs), aiming to enhance the LLM's ability to generalize instruction execution and adapt to user preferences. With the increasing integration of multi-modal…
Large multimodal models (LMMs) excel in adhering to human instructions. However, self-contradictory instructions may arise due to the increasing trend of multimodal interaction and context length, which is challenging for language beginners…
Self-training is an important technique for solving semi-supervised learning problems. It leverages unlabeled data by generating pseudo-labels and combining them with a limited labeled dataset for training. The effectiveness of…
Instruction tuning in multimodal large language models (MLLMs) generally involves cooperative learning between a backbone LLM and a feature encoder of non-text input modalities. The major challenge is how to efficiently find the synergy…
Instruction tuning (IT) achieves impressive zero-shot generalization results by training large language models (LLMs) on a massive amount of diverse tasks with instructions. However, how to select new tasks to improve the performance and…
Large language models (LLMs) have advanced significantly in code generation, yet their ability to follow complex programming instructions with layered and diverse constraints remains underexplored. Existing benchmarks often prioritize…
Instruction tuning, a new learning paradigm that fine-tunes pre-trained language models on tasks specified through instructions, has shown promising zero-shot performance on various natural language processing tasks. However, it has yet to…
Large Language models (LLMs) can generate complicated source code from natural language prompts. However, LLMs can generate output that deviates from what the user wants, requiring supervision and editing. To support this process, we offer…
Instruction following is a critical ability for Large Language Models to perform downstream tasks. The standard approach to instruction tuning has relied on a specific phase of supervised fine-tuning over curated instruction datasets,…
The ability of large language models (LLMs) to follow instructions is crucial to real-world applications. Despite recent advances, several studies have highlighted that LLMs struggle when faced with challenging instructions, especially…