Related papers: BOW: Reinforcement Learning for Bottlenecked Next …

Reinforcement Learning (RL) has shown promise in improving the reasoning abilities of Large Language Models (LLMs). However, the specific challenges of adapting RL to multimodal data and formats remain relatively unexplored. In this work,…

Weakly-supervised learning (WSL) has shown promising results in addressing label scarcity on many NLP tasks, but manually designing a comprehensive, high-quality labeling rule set is tedious and difficult. We study interactive…

Recent advances in large language models (LLMs) have demonstrated significant progress in performing complex tasks. While Reinforcement Learning from Human Feedback (RLHF) has been effective in aligning LLMs with human preferences, it is…

Reinforcement learning (RL) has achieved remarkable success in LLM reasoning, but whether it can also improve direct recall of parametric knowledge remains an open question. We study this question in a controlled zero-shot, one-hop,…

Sampling multiple outputs from a Large Language Model (LLM) and selecting the most frequent (Self-consistency) or highest-scoring (Best-of-N) candidate is a popular approach to achieve higher accuracy in tasks with discrete final answers.…

To predict what someone will say is to model how they think. We study this through next-turn dialogue prediction: given a conversation, predict the next utterance produced by a person. We compare learning approaches along two dimensions:…

Recently, deep reasoning LLMs (e.g., OpenAI o1 and DeepSeek-R1) have shown promising performance in various downstream tasks. Free translation is an important and interesting task in the multilingual world, which requires going beyond…

We show that reinforcement learning with verifiable rewards (RLVR) can elicit strong mathematical reasoning in certain language models even with spurious rewards that have little, no, or even negative correlation with the correct answer.…

Previous language model pre-training methods have uniformly applied a next-token prediction loss to all training tokens. Challenging this norm, we posit that "9l training". Our initial analysis examines token-level training dynamics of…

Modern Artificial Intelligence applications show great potential for language-related tasks that rely on next-word prediction. The current generation of Large Language Models (LLMs) have been linked to claims about human-like linguistic…

Distributed word representation (a.k.a. word embedding) is a key focus in natural language processing (NLP). As a highly successful word embedding model, Word2Vec offers an efficient method for learning distributed word representations on…

Standard Chain-of-Thought (CoT) prompting empowers Large Language Models (LLMs) with reasoning capabilities, yet its reliance on linear natural language is inherently insufficient for effective world modeling in embodied tasks. While text…

Reinforcement learning (RL) has emerged as a promising approach to improve large language model (LLM) reasoning, yet most open efforts focus narrowly on math and code, limiting our understanding of its broader applicability to general…

Large Language Models (LLMs) can reason over natural-language inputs, but their role in intrusion detection without fine-tuning remains uncertain. This study evaluates a prompt-only approach on UNSW-NB15 by converting each network flow to a…

Large language models are increasingly used to support high-stakes decisions, potentially influencing who is granted bail or receives a loan. Naive chain-of-thought sampling can improve average decision accuracy, but has also been shown to…

Reinforcement Learning (RL) has proven to be an effective post-training strategy for enhancing reasoning in vision-language models (VLMs). Group Relative Policy Optimization (GRPO) is a recent prominent method that encourages models to…

Estimating optimal individualized treatment rules (ITRs) via outcome weighted learning (OWL) often relies on observed rewards that are noisy or optimistic proxies for the true latent utility. Ignoring this reward uncertainty leads to the…

Long context reasoning in large language models (LLMs) has demonstrated enhancement of their cognitive capabilities via chain-of-thought (CoT) inference. Training such models is usually done via reinforcement learning with verifiable…

Reinforcement learning (RL) can refine the reasoning abilities of large language models (LLMs), but critically depends on a key prerequisite: the LLM can already generate high-utility reasoning paths with non-negligible probability. For…

Future robotic systems operating in real-world environments will require on-board embodied intelligence without continuous cloud connection, balancing capabilities with constraints on computational power and memory. This work presents an…