Related papers: R2IF: Aligning Reasoning with Decisions via Compos…

Reinforcement Learning from Human Feedback (RLHF) enables powerful LLM alignment but can introduce reward hacking - models exploit spurious correlations in proxy rewards without genuine alignment. Compounding this, the objectives…

Text-to-SQL is a challenging task involving multiple reasoning-intensive subtasks, including natural language understanding, database schema comprehension, and precise SQL query formulation. Existing approaches often rely on handcrafted…

Instruction-following is essential for aligning large language models (LLMs) with user intent. While recent reasoning-oriented models exhibit impressive performance on complex mathematical problems, their ability to adhere to natural…

Despite the success of large language models (LLMs) in various natural language processing (NLP) tasks, the stored knowledge in these models may inevitably be incomplete, out-of-date, or incorrect. This motivates the need to utilize…

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…

While recent advancements in aligning Large Language Models (LLMs) with recommendation tasks have shown great potential and promising performance overall, these aligned recommendation LLMs still face challenges in complex scenarios. This is…

Reinforcement learning (RL) algorithms are highly sensitive to reward function specification, which remains a central challenge limiting their broad applicability. We present ARM-FM: Automated Reward Machines via Foundation Models, a…

Large language models (LLMs) excel at logical and algorithmic reasoning, yet their emotional intelligence (EQ) still lags far behind their cognitive prowess. While reinforcement learning from verifiable rewards (RLVR) has advanced in other…

Large Audio Language Models (LALMs), powered by the chain-of-thought (CoT) paradigm, have shown remarkable reasoning capabilities. Intuitively, different problems often require varying depths of reasoning. While some methods can determine…

Designing reward functions for efficiently guiding reinforcement learning (RL) agents toward specific behaviors is a complex task. This is challenging since it requires the identification of reward structures that are not sparse and that…

We introduce Motif-2-12.7B-Reasoning, a 12.7B parameter language model designed to bridge the gap between open-weight systems and proprietary frontier models in complex reasoning and long-context understanding. Addressing the common…

We propose integration of reasoning into speech large language models (speechLLMs) for the end-to-end slot-filling task. Inspired by the recent development of reasoning LLMs, we use a chain-of-thought framework to decompose the slot-filling…

Large language models for code (i.e., code LLMs) have shown strong code understanding and generation capabilities. To evaluate the capabilities of code LLMs in various aspects, many benchmarks have been proposed (e.g., HumanEval and…

Reinforcement Learning with Verifiable Rewards (RLVR) has markedly enhanced the reasoning abilities of large language models (LLMs). Its success, however, largely depends on strong base models with rich world knowledge, yielding only modest…

Many applications of large language models (LLMs) require deductive reasoning, yet models frequently produce incorrect or redundant inference steps. We frame natural language inference as a search problem where the final answer is the valid…

Reinforcement Learning with Verifiable Rewards (RLVR) improves final-answer accuracy on reasoning tasks, but it does not reliably improve reasoning quality. Because outcome rewards only assess final answers, they also reward spurious…

Large Language Models excel at code generation yet struggle with complex programming tasks that demand sophisticated reasoning. To bridge this gap, traditional process supervision relies on learned reward models requiring costly training…

Reinforcement Learning with Verifiable Rewards (RLVR) has recently demonstrated notable success in enhancing the reasoning performance of large language models (LLMs), particularly on mathematics and programming tasks. Similar to how…

Large language models (LLMs) solve reasoning problems by first generating a rationale and then answering. We formalize reasoning as a latent variable model and derive a reward-based filtered expectation-maximization (FEM) objective for…

Reinforcement learning has recently improved the reasoning ability of Large Language Models and Multimodal LLMs, yet prevailing reward designs emphasise final-answer correctness and consequently tolerate process hallucinations--cases where…