相关论文: Detecting Edit Failures In Large Language Models: …

We propose a constraint learning schema for fine-tuning Large Language Models (LLMs) with attribute control. Given a training corpus and control criteria formulated as a sequence-level constraint on model outputs, our method fine-tunes the…

Vision-Language Models (VLMs) excel at multimodal reasoning, yet it remains unclear whether their answers are grounded in visual evidence or driven by learned language and world priors. Counting provides a precise testbed: when visual…

Local factual edits in scientific manuscripts often create non-local revision obligations. If a dataset changes from 215 to 80 documents, claims such as 'medium-scale' or 'a few hundred items' may also become stale, even though they do not…

Large language models (LLMs) are commonly evaluated on tasks that test their knowledge or reasoning abilities. In this paper, we explore a different type of evaluation: whether an LLM can predict aspects of its own responses. Since LLMs…

Large language models (LLMs) exhibit remarkable capabilities across diverse tasks, yet aligning them efficiently and effectively with human expectations remains a critical challenge. This thesis advances LLM alignment by introducing novel…

Supervised fine-tuning (SFT) of large language models can be viewed as an off-policy learning problem, where expert demonstrations come from a fixed behavior policy while training aims to optimize a target policy. Importance sampling is the…

Large Language Models (LLMs) based on the pre-trained fine-tuning paradigm have become pivotal in solving natural language processing tasks, consistently achieving state-of-the-art performance. Nevertheless, the theoretical understanding of…

We propose a self-correction mechanism for Large Language Models (LLMs) to mitigate issues such as toxicity and fact hallucination. This method involves refining model outputs through an ensemble of critics and the model's own feedback.…

Deploying Large Language Models (LLMs) in medical applications requires fact-checking capabilities to ensure patient safety and regulatory compliance. We introduce MedFact, a challenging Chinese medical fact-checking benchmark with 2,116…

In real-world machine learning systems, labels are often derived from user behaviors that the system wishes to encourage. Over time, new models must be trained as new training examples and features become available. However, feedback loops…

Knowledge Editing, which efficiently modifies the knowledge in large language models, has gathered great attention. Current benchmarks primarily use multi-hop question answering to assess and analyze newly injected or updated knowledge.…

The increasing use of Machine Learning (ML) software can lead to unfair and unethical decisions, thus fairness bugs in software are becoming a growing concern. Addressing these fairness bugs often involves sacrificing ML performance, such…

Large language models (LLMs) have achieved impressive results across a range of natural language processing tasks, but their potential to generate harmful content has raised serious safety concerns. Current toxicity detectors primarily rely…

Large language models (LLMs) have become essential tools in software development, widely used for requirements engineering, code generation and review tasks. Software engineers often rely on LLMs to verify if code implementation satisfy…

While recent works have been considerably improving the quality of the natural language explanations (NLEs) generated by a model to justify its predictions, there is very limited research in detecting and alleviating inconsistencies among…

To continuously improve quality and reflect changes in data, machine learning applications have to regularly retrain and update their core models. We show that a differential analysis of language model snapshots before and after an update…

Large language models (LLMs) excel at generating long-form responses, but evaluating their factuality remains challenging due to complex inter-sentence dependencies within the generated facts. Prior solutions predominantly follow a…

Many evaluations of Large Language Models (LLMs) target tasks that are inherently ill-defined, with unclear input and output spaces and ambiguous success criteria. We analyze why existing evaluation benchmarks and metrics fail to provide…

Target-oriented multimodal sentiment classification seeks to predict sentiment polarity for specific targets from image-text pairs. While existing works achieve competitive performance, they often over-rely on textual content and fail to…

Large language models (LLMs) require frequent knowledge updates to reflect changing facts and mitigate hallucinations. To meet this demand, lifelong knowledge editing has emerged as a continual approach to modify specific pieces of…