Related papers: STEER: Inference-Time Risk Control via Constrained…

Despite efforts to align large language models (LLMs) with societal and moral values, these models remain susceptible to jailbreak attacks -- methods designed to elicit harmful responses. Jailbreaking black-box LLMs is considered…

Large language models (LLMs) can store a significant amount of factual knowledge in their parameters. However, their parametric knowledge may conflict with the information provided in the context -- this phenomenon, known as…

Large Language Models (LLMs) suffer significant performance degradation in multi-turn conversations when information is presented incrementally. Given that multi-turn conversations characterize everyday interactions with LLMs, this…

Assessing the quality of outputs generated by generative models, such as large language models and vision language models, presents notable challenges. Traditional methods for evaluation typically rely on either human assessments, which are…

End-to-end automatic speech recognition (ASR) systems frequently misrecognize domain-specific phrases like named entities, which can cause catastrophic failures in downstream tasks. A new family of named entity correction methods based on…

Retrieval-Augmented Generation (RAG) systems for Large Language Models (LLMs) hold promise in knowledge-intensive tasks but face limitations in complex multi-step reasoning. While recent methods have integrated RAG with chain-of-thought…

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…

Discrete biological sequence optimization requires iterative refinement under strict syntactic constraints. Diffusion models offer progressive refinement but do not naturally expose controllable discrete edit operations, while…

Fine-tuning Large Language Models (LLMs) on specific datasets is a common practice to improve performance on target tasks. However, this performance gain often leads to overfitting, where the model becomes too specialized in either the task…

State-of-the-art language model fine-tuning techniques, such as Direct Preference Optimization (DPO), restrict user control by hard-coding predefined behaviors into the model. To address this, we propose a novel method, Configurable Safety…

Responsible deployment of language models requires mechanisms for refusing unsafe prompts while preserving model performance. While most approaches modify model weights through additional training, we explore an alternative: steering model…

Recent Large Reasoning Models (LRMs) have achieved remarkable progress on task-specific benchmarks, yet their evaluation methods remain constrained by isolated problem-solving paradigms. Existing benchmarks predominantly assess…

Empirical risk minimization (ERM) is typically designed to perform well on the average loss, which can result in estimators that are sensitive to outliers, generalize poorly, or treat subgroups unfairly. While many methods aim to address…

In recent years, Large Language Models (LLMs) have demonstrated remarkable generative abilities, but can they judge the quality of their own generations? A popular concept, referred to as self-refinement, postulates that LLMs can detect and…

We present DRESS, a large vision language model (LVLM) that innovatively exploits Natural Language feedback (NLF) from Large Language Models to enhance its alignment and interactions by addressing two key limitations in the state-of-the-art…

Information extraction tasks such as event extraction require an in-depth understanding of the output structure and sub-task dependencies. They heavily rely on task-specific training data in the form of (passage, target structure) pairs to…

Large language models can exhibit emergent reasoning behaviors, often manifested as recurring lexical patterns (e.g., "wait," indicating verification). However, complex reasoning trajectories remain sparse in unconstrained sampling, and…

There is increasing interest in using LLMs as decision-making "agents." Doing so includes many degrees of freedom: which model should be used; how should it be prompted; should it be asked to introspect, conduct chain-of-thought reasoning,…

Recent advances in domain adaptation show that deep self-training presents a powerful means for unsupervised domain adaptation. These methods often involve an iterative process of predicting on target domain and then taking the confident…

Function calling enables large language models (LLMs) to interact with external systems by leveraging tools and APIs. When faced with multi-step tool usage, LLMs still struggle with tool selection, parameter generation, and tool-chain…