Related papers: Chunky Post-Training: Data Driven Failures of Gene…

Instruction tuning -- supervised fine-tuning using instruction-response pairs -- is a key step in making pre-trained large language models (LLMs) instructable. Meanwhile, LLMs perform multitask learning during their pre-training, acquiring…

In autoregressive large language models (LLMs), temporal straightening offers an account of how the next-token prediction objective shapes representations. Models learn to progressively straighten the representational trajectory of input…

Synthetically-generated data plays an increasingly larger role in training large language models. However, while synthetic data has been found to be useful, studies have also shown that without proper curation it can cause LLM performance…

Overfitting data is a well-known phenomenon related with the generation of a model that mimics too closely (or exactly) a particular instance of data, and may therefore fail to predict future observations reliably. In practice, this…

Anticipating supply chain disruptions before they materialize is a core challenge for firms and policymakers alike. A key difficulty is learning to reason reliably about infrequent, high-impact events from noisy and unstructured inputs - a…

Large language models (LLMs) are known to generate politically biased text. Yet, it remains unclear how such biases arise, making it difficult to design effective mitigation strategies. We hypothesize that these biases are rooted in the…

Instruction tuning on a mixture of tasks has improved zero-shot capabilities in natural language processing (NLP). Nevertheless, existing methods often learn features that exhibit correlations between instruction-formatted samples and…

Personality traits have long been studied as predictors of human behavior. Recent advances in Large Language Models (LLMs) suggest similar patterns may emerge in artificial systems, with advanced LLMs displaying consistent behavioral…

Neural networks have a number of shortcomings. Amongst the severest ones is the sensitivity to distribution shifts which allows models to be easily fooled into wrong predictions by small perturbations to inputs that are often imperceivable…

Post-training fundamentally alters the behavior of large language models (LLMs), yet its impact on the internal parameter space remains poorly understood. In this work, we conduct a systematic singular value decomposition (SVD) analysis of…

As LLMs occupy an increasingly important role in society, they are more and more confronted with questions that require them not only to draw on their general knowledge but also to align with certain human value systems. Therefore, studying…

Using responses generated by high-performing large language models (LLMs) for instruction tuning has become a widely adopted approach. However, the existing literature overlooks a property of LLM-generated responses: they conflate world…

Large language models (LLMs) often miscommunicate their uncertainty: repeated queries can produce divergent answers, yet generated responses are typically unhedged or hedged in ways that do not reflect this variability. This conveys…

Work on continual learning (CL) has thus far largely focused on the problems arising from shifts in the data distribution. However, CL can be decomposed into two sub-problems: (a) shifts in the data distribution, and (b) dealing with the…

Spurious correlations in a reward model's training data can prevent Reinforcement Learning from Human Feedback (RLHF) from identifying the desired goal and induce unwanted behaviors. This paper shows that offline RLHF is susceptible to…

Post-training has become central to turning pretrained large language models (LLMs) into aligned, capable, and deployable systems. Recent progress spans supervised fine-tuning (SFT), preference optimization, reinforcement learning (RL),…

Unraveling the intricate details of events in natural language necessitates a subtle understanding of temporal dynamics. Despite the adeptness of Large Language Models (LLMs) in discerning patterns and relationships from data, their…

Transformer-based large models excel in natural language processing and computer vision, but face severe computational inefficiencies due to the self-attention's quadratic complexity with input tokens. Recently, researchers have proposed a…

Recent advancements in large language models (LLMs) reveal a perplexing phenomenon in continual learning: despite extensive training, models experience significant performance declines, raising questions about task alignment and underlying…

Large Language Models (LLMs) have achieved remarkable success, where instruction tuning is the critical step in aligning LLMs with user intentions. In this work, we investigate how the instruction tuning adjusts pre-trained models with a…