Related papers: When Rubrics Fail: Error Enumeration as Reward in …

Text-to-SQL, a pivotal natural language processing (NLP) task that converts textual queries into executable SQL, has seen substantial progress in recent years. However, existing evaluation and reward mechanisms used to train and assess the…

Recently, object counting has shifted towards class-agnostic counting (CAC), which counts instances of arbitrary object classes never seen during model training. With advancements in robust vision-and-language foundation models, there is a…

Modern recommender systems must adapt to dynamic, need-specific objectives for diverse recommendation scenarios, yet most traditional recommenders are optimized for a single static target and struggle to reconfigure behavior on demand.…

Language models must be adapted to understand and follow user instructions. Reinforcement learning is widely used to facilitate this -- typically using fixed criteria such as "helpfulness" and "harmfulness". In our work, we instead propose…

Referring expression comprehension (REC) aims to localize a target object within an image based on a given expression. Although recent advances in vision-language models have led to substantial improvements in REC tasks, current REC…

As Large Language Model (LLM) alignment evolves from simple completions to complex, highly sophisticated generation, Reward Models are increasingly shifting toward rubric-guided evaluation to mitigate surface-level biases. However, the…

Video reasoning has advanced with large multimodal models (LMMs), yet their inference is often a single pass that returns an answer without verifying whether the reasoning is evidence-aligned. We introduce Reinforce to Learn, Elect to…

While model-based verifiers are essential for scaling Reinforcement Learning with Verifiable Rewards (RLVR), current outcome-centric verification paradigms primarily focus on the consistency between the final result and the ground truth,…

Robust evaluation is critical for deploying trustworthy retrieval-augmented generation (RAG) systems. However, current LLM-based evaluation frameworks predominantly rely on directly prompting resource-intensive models with complex…

Recent advances in reinforcement learning (RL) have predominantly leveraged neural network policies for decision-making, yet these models often lack interpretability, posing challenges for stakeholder comprehension and trust. Concept…

Reject Inference (RI) methods aim to address sample bias by inferring missing repayment data for rejected credit applicants. Traditional approaches often assume that the behavior of rejected clients can be extrapolated from accepted…

Reward models (RMs) are fundamental to aligning Large Language Models (LLMs) via human feedback, yet they often suffer from reward hacking. They tend to latch on to superficial or spurious attributes, such as response length or formatting,…

Referring Expression Comprehension (REC) aims to localize the image region corresponding to a natural language query. Recent neuro-symbolic REC approaches leverage large language models (LLMs) and vision-language models (VLMs) to perform…

Process Reward Models (PRMs) have achieved strong results in complex reasoning, but are bottlenecked by costly process-level supervision. A widely used alternative, Monte Carlo Estimation (MCE), defines process rewards as the probability…

Reinforcement Learning with Verifiable Rewards (RLVR) improves multimodal reasoning by rewarding verifiable final answers. Yet answer-correct trajectories may still rely on incomplete derivations, weak evidence, or statements that…

Automated code review comment generation (RCG) aims to assist developers by automatically producing natural language feedback for code changes. Existing approaches are primarily either generation-based, using pretrained language models, or…

Reinforcement Learning (RL) is one of the most dynamic research areas in Game AI and AI as a whole, and a wide variety of games are used as its prominent test problems. However, it is subject to the replicability crisis that currently…

Language models can use verifiable rewards to improve at a wide variety of reasoning tasks. However, both parametric (e.g. RLVR) and non-parametric (e.g. prompt optimization) approaches to doing so typically require hundreds of training…

Explainable recommendation systems (RSs) are designed to explicitly uncover the rationale of each recommendation, thereby enhancing the transparency and credibility of RSs. Previous methods often jointly predicted ratings and generated…

Large language models (LLMs) excel at reasoning, yet post-training remains critical for aligning their behavior with task goals. Existing reinforcement learning (RL) methods often depend on costly human annotations or external reward…