Related papers: Think before you speak: Training Language Models W…
Overparameterized large-scale language models have impressive generalization performance of in-context few-shot learning. However, most language models allocate the same amount of parameters or computation to each token, disregarding the…
Pause insertion, also known as phrase break prediction and phrasing, is an essential part of TTS systems because proper pauses with natural duration significantly enhance the rhythm and intelligibility of synthetic speech. However,…
Hybrid reasoning language models are commonly controlled through high-level Think/No-think instructions to regulate reasoning behavior, yet we found that such mode switching is largely driven by a small set of trigger tokens rather than the…
Large language models are classically trained in stages: pretraining on raw text followed by post-training for instruction following and reasoning. However, this separation creates a fundamental limitation: many desirable behaviors such as…
Scaling up language models has led to unprecedented performance gains, but little is understood about how the training dynamics change as models get larger. How do language models of different sizes learn during pre-training? Why do larger…
Techniques enabling large language models (LLMs) to "think more" by generating and attending to intermediate reasoning steps have shown promise in solving complex problems. However, the standard approaches generate sequences of discrete…
Recent studies show that the reasoning capabilities of Large Language Models (LLMs) can be improved by applying Reinforcement Learning (RL) to question-answering (QA) tasks in areas such as math and coding. With a long context length, LLMs…
Evaluating the abilities of large language models (LLMs) for tasks that require long-term memory and thus long-context reasoning, for example in conversational settings, is hampered by the existing benchmarks, which often lack narrative…
This paper presents a novel open-domain dialogue generation model emphasizing the differentiation of speakers in multi-turn conversations. Differing from prior work that solely relies on the content of conversation history to generate a…
Recently, prompt tuning \cite{lester2021power} has gradually become a new paradigm for NLP, which only depends on the representation of the words by freezing the parameters of pre-trained language models (PLMs) to obtain remarkable…
The most common training pipeline for large language models includes pretraining, finetuning and aligning phases, with their respective resulting models, such as the pretrained model and the finetuned model. Finetuned and aligned models…
The scalability of large language models for long-context reasoning is severely constrained by the linear growth of their Transformer key-value cache, which incurs significant memory and computational costs. We posit that as a model…
The development of state-of-the-art large language models is commonly understood as a two-stage process involving pre-training and post-training. We point out the need for an additional intermediate stage called reinforcement mid-training…
Temporal reasoning over long, multi-session dialogues is a critical capability for conversational agents. However, existing works and our pilot study have shown that as dialogue histories grow in length and accumulate noise, current…
Existing large language models have to run K times to generate a sequence of K tokens. In this paper, we present RecycleGPT, a generative language model with fast decoding speed by recycling pre-generated model states without running the…
Researchers have explored different ways to improve large language models (LLMs)' capabilities via dummy token insertion in contexts. However, existing works focus solely on the dummy tokens themselves, but fail to leverage the inherent…
The pre-training of masked language models (MLMs) consumes massive computation to achieve good results on downstream NLP tasks, resulting in a large carbon footprint. In the vanilla MLM, the virtual tokens, [MASK]s, act as placeholders and…
This technical report describes the design and training of novel speculative decoding draft models, for accelerating the inference speeds of large language models in a production environment. By conditioning draft predictions on both…
Compute scaling for language model (LM) pretraining has outpaced the growth of human-written texts, leading to concerns that data will become the bottleneck to LM scaling. To continue scaling pretraining in this data-constrained regime, we…
We consider the question: when a large language reasoning model makes a choice, did it think first and then decide to, or decide first and then think? In this paper, we present evidence that detectable, early-encoded decisions shape…