相关论文: Suri: Multi-constraint Instruction Following for L…

Successful sequential recommendation systems rely on accurately capturing the user's short-term and long-term interest. Although Transformer-based models achieved state-of-the-art performance in the sequential recommendation task, they…

Understanding user queries is fundamental in many applications, such as home assistants, booking systems, or recommendations. Accordingly, it is crucial to develop accurate Spoken Language Understanding (SLU) approaches to ensure the…

Self-correction is a highly desirable capability of large language models (LLMs), yet it has consistently been found to be largely ineffective in modern LLMs. Current methods for training self-correction typically depend on either multiple…

Modern information retrieval (IR) models, trained exclusively on standard <query, passage> pairs, struggle to effectively interpret and follow explicit user instructions. We introduce InF-IR, a large-scale, high-quality training corpus…

Text generation under constraints have seen increasing interests in natural language processing, especially with the rapidly improving capabilities of large language models. However, existing benchmarks for constrained generation usually…

Large language models (LLMs) have shown great potential in natural language processing tasks, but their application to machine translation (MT) remains challenging due to pretraining on English-centric data and the complexity of…

Large Reasoning Models (LRMs) have achieved remarkable success, yet they often suffer from producing unnecessary and verbose reasoning chains. We identify a core aspect of this issue as "invalid thinking" -- models tend to repeatedly…

Generating long, coherent text remains a challenge for large language models (LLMs), as they lack hierarchical planning and structured organization in discourse generation. We introduce Structural Alignment, a novel method that aligns LLMs…

Large language models (LLMs) have advanced significantly in code generation, yet their ability to follow complex programming instructions with layered and diverse constraints remains underexplored. Existing benchmarks often prioritize…

Language model (LM) post-training relies on two stages of human supervision: task demonstrations for supervised finetuning (SFT), followed by preference comparisons for reinforcement learning from human feedback (RLHF). As LMs become more…

The rapidly increasing capabilities of large language models (LLMs) raise an urgent need to align AI systems with diverse human preferences to simultaneously enhance their usefulness and safety, despite the often conflicting nature of these…

To combat the misuse of Large Language Models (LLMs), many recent studies have presented LLM-generated-text detectors with promising performance. When users instruct LLMs to generate texts, the instruction can include different constraints…

Large language models (LLMs) have demonstrated outstanding performance in natural language processing tasks. However, in the field of recommender systems, due to the inherent structural discrepancy between user behavior data and natural…

Large Language Models (LLMs) show potential as sequential decision-making agents, but their application is often limited due to a reliance on large, computationally expensive models. This creates a need to improve smaller models, yet…

Recent advancements in open-source code large language models (LLMs) have been driven by fine-tuning on the data generated from powerful closed-source LLMs, which are expensive to obtain. This paper explores whether it is possible to use a…

Training large language models (LLMs) with open-domain instruction following data brings colossal success. However, manually creating such instruction data is very time-consuming and labor-intensive. Moreover, humans may struggle to produce…

Large Language Models (LLMs) exhibit remarkable generative capabilities, enabling the generation of valuable information. Despite these advancements, previous research found that LLMs sometimes struggle with adhering to specific constraints…

Recent advancements in large language models (LLMs) have enabled in-context learning (ICL)-based methods that significantly outperform fine-tuning approaches for text-to-SQL tasks. However, their performance is still considerably lower than…

Recent work has described neural-network-based agents that are trained with reinforcement learning (RL) to execute language-like commands in simulated worlds, as a step towards an intelligent agent or robot that can be instructed by human…

Current safety alignment techniques for large language models (LLMs) face two key challenges: (1) under-generalization, which leaves models vulnerable to novel jailbreak attacks, and (2) over-alignment, which leads to the excessive refusal…