相关论文: Generalizing Verifiable Instruction Following

Recent LLMs have shown remarkable success in following user instructions, yet handling instructions with multiple constraints remains a significant challenge. In this work, we introduce WildIFEval - a large-scale dataset of 7K real user…

A central belief in scaling reinforcement learning with verifiable rewards for instruction following (IF) tasks is that, a diverse mixture of verifiable hard and unverifiable soft constraints is essential for generalizing to unseen…

Instruction following is critical for LLMs deployed in enterprise and API-driven settings, where strict adherence to output formats, content constraints, and procedural requirements is essential for enabling reliable LLM-assisted workflows.…

As large language models (LLMs) are increasingly applied to real-world scenarios, it becomes crucial to understand their ability to follow multiple instructions simultaneously. To systematically evaluate these capabilities, we introduce two…

Task semantics can be expressed by a set of input-output examples or a piece of textual instruction. Conventional machine learning approaches for natural language processing (NLP) mainly rely on the availability of large-scale sets of…

Reinforcement Learning from Human Feedback has become the standard paradigm for language model alignment, where reward models directly determine alignment effectiveness. In this work, we focus on how to evaluate the generalizability of…

We introduce VisIT-Bench (Visual InsTruction Benchmark), a benchmark for evaluation of instruction-following vision-language models for real-world use. Our starting point is curating 70 'instruction families' that we envision instruction…

Large language models (LLMs) could be valuable personal AI agents across various domains, provided they can precisely follow user instructions. However, recent studies have shown significant limitations in LLMs' instruction-following…

Although Large Language Models (LLMs) have demonstrated strong ability, they are further supposed to be controlled and guided by in real-world scenarios to be safe, accurate, and intelligent. This demands the possession of capability of…

Retriever-augmented instruction-following models are attractive alternatives to fine-tuned approaches for information-seeking tasks such as question answering (QA). By simply prepending retrieved documents in its input along with an…

Large language models have achieved significant reasoning improvements through reinforcement learning with verifiable rewards (RLVR). Yet as model capabilities grow, constructing high-quality reward signals becomes increasingly difficult,…

Instruction following has catalyzed the recent era of Large Language Models (LLMs) and is the foundational skill underpinning more advanced capabilities such as reasoning and agentic behaviors. As tasks grow more challenging, the logic…

The application scope of large language models (LLMs) is increasingly expanding. In practical use, users might provide feedback based on the model's output, hoping for a responsive model that can complete responses according to their…

Evaluating LLMs' instruction-following ability in multi-topic dialogues is essential yet challenging. Existing benchmarks are limited to a fixed number of turns, susceptible to saturation and failing to account for users' interactive…

Reinforcement Learning from Verifiable Rewards (RLVR) has emerged as a powerful paradigm for enhancing Large Language Models (LLMs), exemplified by the success of OpenAI's o-series. In RLVR, rewards are derived from verifiable signals-such…

Recent neural theorem provers use reinforcement learning with verifiable rewards (RLVR), where proof assistants provide binary correctness signals. While verifiable rewards are cheap and scalable without reward hacking issues, they suffer…

Imitation learning benchmarks often lack sufficient variation between training and evaluation, limiting meaningful generalisation assessment. We introduce Labyrinth, a benchmarking environment designed to test generalisation with precise…

We introduce MIA-Bench, a new benchmark designed to evaluate multimodal large language models (MLLMs) on their ability to strictly adhere to complex instructions. Our benchmark comprises a diverse set of 400 image-prompt pairs, each crafted…

In real-world task-oriented dialogue (TOD) settings, agents are required to strictly adhere to complex instructions while conducting multi-turn conversations with customers. These instructions are typically presented in natural language…

Reward Models, essential for guiding Large Language Model optimization, are typically trained on fixed preference datasets, resulting in rigid alignment to single, implicit preference distributions. This prevents adaptation to diverse…