14 accepted papers
Post-training for reasoning in large language models has increasingly relied on verifiable rewards: deterministic checkers that provide $0$–$1$ correctness signals. While reliable, such binary feedback is brittle—many tasks admit partially correct or alternative answers that verifiers under-credit,…
The progress of AI is bottlenecked by the quality of evaluation, making powerful LLM-as-a-Judge models a core solution. The efficacy of these judges depends on their chain-of-thought reasoning, creating a critical need for methods that can effectively optimize this reasoning process. In this work, w…
Reinforcement learning with human-annotated data has boosted chain-of-thought reasoning in large reasoning models, but these gains come at high costs in labeled data while faltering on harder tasks. A natural next step is experience-driven learning, where models improve without curated labels by ada…
To achieve faithful reasoning that aligns with human expectations, large language models (LLMs) need to ground their reasoning to real-world knowledge (e.g., web facts, math and physical rules). Tools help LLMs access this external knowledge, but there remains challenges for fine-tuning LLM agents (…
Aligned instruction following models can better fulfill user requests than their unaligned counterparts. However, it has been shown that there is a length bias in evaluation of such models, and that training algorithms tend to exploit this bias by learning longer responses. In this work we show how
Training data quality is one of the most important drivers of final model quality. In this work, we introduce a method for evaluating data integrity based on the assumption that low-quality input prompts result in high variance and low quality responses. This is achieved by measuring the rejected re…
We present a scalable method to build a high quality instruction following language model by automatically labelling human-written text with corresponding instructions. Our approach, named instruction backtranslation, starts with a language model finetuned on a small amount of seed data, and a given…
Large Language Models (LLMs) have demonstrated remarkable generative abilities, but can they judge the quality of their own generations and self-improve?A popular concept, referred to as *self-refinement*, postulates that LLMs can detect and correct the errors in their generations when asked to do s…
Recent advancements in large language models have enabled them to perform well on complex tasks that require step-by-step reasoning with few-shot learning. However, it is unclear whether these models are applying reasoning skills they have learnt during pre-training , or if they are simply memorizin…
Large language models are trained in two stages: (1) unsupervised pretraining from raw text, to learn general-purpose representations, and (2) large scale instruction tuning and reinforcement learning, to better align to end tasks and user preferences. We measure the relative importance of these tw…
Though remarkable efforts have been made in non-parallel text style transfer, the evaluation system is unsatisfactory. It always evaluates over samples from only one checkpoint of the model and compares three metrics, i.e., transfer accuracy, BLEU score, and PPL score. In this paper, we argue the in…
Meta learning has been making impressive progress for fast model adaptation. However, limited work has been done on learning fast uncertainty adaption for Bayesian modeling. In this paper, we propose to achieve the goal by placing meta learning on the space of probability measures, inducing the conc…
The instability in GANs’ training has been a long-standing problem despite remarkable research efforts. We identify that instability issues stem from difficulties of performing feature matching with mini-batch statistics, due to a fragile balance between the fixed target distribution and the progres…
Generating long-range skeleton-based human actions has been a challenging problem since small deviations of one frame can cause an malformed action sequence. Most existing methods borrow ideas from video generation that naively treat skeleton nodes/joints as pixels of images without considering the…