Related papers: Instability in Downstream Task Performance During …
Existing research has shown that a multilingual pre-trained language model fine-tuned with one (source) language also performs well on downstream tasks for non-source languages, even though no fine-tuning is done on these languages.…
Unlearning methods have the potential to improve the privacy and safety of large language models (LLMs) by removing sensitive or harmful information post hoc. The LLM unlearning research community has increasingly turned toward empirical…
The use of Large Language Models (LLMs) in software engineering tasks is growing, especially in the areas of bug fixing and code generation. Nevertheless, these models often yield unstable results; when executed at different times with the…
Pre-training has achieved remarkable success when transferred to downstream tasks. In machine learning, we care about not only the good performance of a model but also its behavior under reasonable shifts of condition. The same philosophy…
Fine-tuning significantly improves the performance of Large Language Models (LLMs), yet its underlying mechanisms remain poorly understood. This paper aims to provide an in-depth interpretation of the fine-tuning process through circuit…
Vision-Language Pretraining (VLP) models have recently successfully facilitated many cross-modal downstream tasks. Most existing works evaluated their systems by comparing the fine-tuned downstream task performance. However, only average…
Fine-tuning pre-trained language models on downstream tasks with varying random seeds has been shown to be unstable, especially on small datasets. Many previous studies have investigated this instability and proposed methods to mitigate it.…
Large language models (LLMs) are trained for downstream tasks by updating their parameters (e.g., via RL). However, updating parameters forces them to absorb task-specific information, which can result in catastrophic forgetting and loss of…
Training stability of large language models(LLMs) is an important research topic. Reproducing training instabilities can be costly, so we use a small language model with 830M parameters and experiment with higher learning rates to force…
The rapid proliferation of large language models (LLMs) such as GPT-4 and Gemini underscores the intense demand for resources during their training processes, posing significant challenges due to substantial computational and environmental…
As large language models (LLMs) are increasingly deployed in high-stakes and operational settings, evaluation strategies based solely on aggregate accuracy are often insucient to characterize system reliability. This study proposes a…
Reinforcement learning (RL) has become the core post-training technique for large language models (LLMs). RL for LLMs involves two stages: generation and training. The LLM first generates samples online, which are then used to derive…
Large language models achieve high performance on many but not all downstream tasks. The interaction between pretraining data and task data is commonly assumed to determine this variance: a task with data that is more similar to a model's…
Instruction tuning significantly enhances the performance of large language models (LLMs) across various tasks. However, the procedure to optimizing the mixing of instruction datasets for LLM fine-tuning is still poorly understood. This…
Large language models are increasingly used as automated evaluators in research and enterprise settings, a practice known as LLM-as-a-judge. While prior work has examined accuracy, bias, and alignment with human preferences, far less…
Downstream scaling laws aim to predict task performance at larger scales from the model's performance at smaller scales. Whether such prediction should be possible is unclear: some works discover clear linear scaling trends after simple…
When learning behavior, training data is often generated by the learner itself; this can result in unstable training dynamics, and this problem has particularly important applications in safety-sensitive real-world control tasks such as…
Large language models are increasingly deployed across diverse applications. This often includes tasks LLMs have not encountered during training. This implies that enumerating and obtaining the high-quality training data for all tasks is…
Reasoning failures in large language models (LLMs) are typically measured only at the end of a generation, yet many failures manifest as a process-level breakdown: the model "loses the thread" mid-reasoning. We study whether such breakdowns…
Large Language Models (LLMs) excel at long-context understanding but exhibit significant limitations in long-form generation. Existing studies primarily focus on single-generation quality, generally overlooking the volatility of the output.…