相关论文: AdaRubric: Task-Adaptive Rubrics for Reliable LLM …

Aligning Multimodal Large Language Models (MLLMs) requires reliable reward models, yet existing single-step evaluators can suffer from lazy judging, exploiting language priors over fine-grained visual verification. While rubric-based…

Techniques for reliable rubric-based LLM evaluation -- ensemble judging, bias mitigation, few-shot calibration -- are scattered across papers with inconsistent terminology and partial implementations. We introduce Autorubric, an open-source…

We propose AdaRec, a few-shot in-context learning framework that leverages large language models for an adaptive personalized recommendation. AdaRec introduces narrative profiling, transforming user-item interactions into natural language…

The evaluation paradigm of LLM-as-judge gains popularity due to its significant reduction in human labor and time costs. This approach utilizes one or more large language models (LLMs) to assess the quality of outputs from other LLMs.…

Deep Research (DR) is an emerging agent application that leverages large language models (LLMs) to address open-ended queries. It requires the integration of several capabilities, including multi-step reasoning, cross-document synthesis,…

Web agents enable users to perform tasks on web browsers through natural language interaction. Evaluating web agents trajectories is an important problem, since it helps us determine whether the agent successfully completed the tasks.…

Standard reward models typically predict scalar scores that fail to capture the multifaceted nature of response quality in non-verifiable domains, such as creative writing or open-ended instruction following. To address this limitation, we…

Robust reinforcement learning (Robust RL) seeks to handle epistemic uncertainty in environment dynamics, but existing approaches often rely on nested min--max optimization, which is computationally expensive and yields overly conservative…

As agents based on large language models are increasingly deployed to long-horizon tasks, maintaining their alignment with stakeholder preferences becomes critical. Effective alignment in such settings requires reward models that are…

LLM alignment remains a critical challenge. Inference-time methods provide a flexible alternative to fine-tuning, but their uniform computational effort often yields suboptimal alignment. We hypothesize that for many alignment tasks, the…

Equipping large language models (LLMs) with search engines via reinforcement learning (RL) has emerged as an effective approach for building search agents. However, overreliance on search introduces unnecessary cost and risks exposure to…

Large language models (LLMs) have recently demonstrated the potential in acting as autonomous agents for sequential decision-making tasks. However, most existing methods either take actions greedily without planning or rely on static plans…

Large Language Models (LLMs) have demonstrated significant success across various domains. However, their application in complex decision-making tasks frequently necessitates intricate prompt engineering or fine-tuning, leading to…

This paper introduces a framework for the automated evaluation of natural language texts. A manually constructed rubric describes how to assess multiple dimensions of interest. To evaluate a text, a large language model (LLM) is prompted…

Scalar reward models compress multi-dimensional human preferences into a single opaque score, creating an information bottleneck that often leads to brittleness and reward hacking in open-ended alignment. We argue that robust alignment for…

With the rise of language and multimodal models of ever-increasing size, pretraining a general-purpose foundational model and adapting it to downstream tasks has become common practice. To this end, adaptation efficiency can be a critical…

Recently, rubrics have been used to guide LLM judges in capturing subjective, nuanced, multi-dimensional human preferences, and have been extended from evaluation to reward signals for reinforcement fine-tuning (RFT). However, rubric…

LLMs often need effective configurations, like temperature and reasoning steps, to handle tasks requiring sophisticated reasoning and problem-solving, ranging from joke generation to mathematical reasoning. Existing prompting approaches…

Aligning multimodal generative models with human preferences demands reward signals that respect the compositional, multi-dimensional structure of human judgment. Prevailing RLHF approaches reduce this structure to scalar or pairwise…

High-quality datasets are fundamental to training and evaluating machine learning models, yet their creation-especially with accurate human annotations-remains a significant challenge. Many dataset paper submissions lack originality,…