相关论文: CMD: a framework for Context-aware Model self-Deto…

Large Language Models (LLMs) have demonstrated great potential as generalist assistants, showcasing powerful task understanding and problem-solving capabilities. To deploy LLMs as AI assistants, it is crucial that these models exhibit…

Large language models (LLMs) exhibit severe multilingual safety misalignment: they possess strong safeguards in high-resource languages but remain highly vulnerable to jailbreak attacks in low-resource languages. Current safety alignment…

Despite notable advances in large language models (LLMs), reliable evaluation of text generation tasks such as text style transfer (TST) remains an open challenge. Existing research has shown that automatic metrics often correlate poorly…

Large Language Models (LLMs) have garnered widespread attention due to their remarkable performance across various tasks. However, to mitigate the issue of hallucinations, LLMs often incorporate retrieval-augmented pipeline to provide them…

Large language models (LLMs) with extended context windows have made significant strides yet remain a challenge due to the scarcity of long documents. Existing methods tend to synthesize long-context data but lack a clear mechanism to…

The rapid advancement of multimodal large language models (MLLMs) has significantly enhanced performance across benchmarks. However, data contamination-unintentional memorization of benchmark data during model training-poses critical…

Standard decoding in Masked Diffusion Models (MDMs) is hindered by context rigidity: tokens are retained based on transient high confidence, often ignoring that early predictions lack full context. This creates cascade effects where initial…

Large language models accumulate extensive parametric knowledge through pre-training. However, knowledge conflicts occur when outdated or incorrect parametric knowledge conflicts with external knowledge in the context. Existing methods…

Large language models (LLMs) can be influenced by harmful or irrelevant context, which can significantly harm model performance on downstream tasks. This motivates principled designs in which LLM systems include built-in mechanisms to guard…

Large language models frequently generate toxic, hateful, or harmful content, yet existing mitigation methods rely on costly retraining or output-level filtering with no mechanistic insight into where toxicity originates internally. We…

Large Language Models (LLMs) encode vast amounts of parametric knowledge during pre-training. As world knowledge evolves, effective deployment increasingly depends on their ability to faithfully follow externally retrieved context. When…

The spread of toxic content online is an important problem that has adverse effects on user experience online and in our society at large. Motivated by the importance and impact of the problem, research focuses on developing solutions to…

In the digital world, memes present a unique challenge for content moderation due to their potential to spread harmful content. Although detection methods have improved, proactive solutions such as intervention are still limited, with…

Large Language Models (LLMs) demonstrate exceptional performance across diverse tasks by leveraging pre-trained (i.e., parametric) and external (i.e., contextual) knowledge. While substantial efforts have been made to enhance the…

A challenge in mitigating social bias in fine-tuned language models (LMs) is the potential reduction in language modeling capability, which can harm downstream performance. Counterfactual data augmentation (CDA), a widely used method for…

WARNING: This paper contains examples of offensive materials. To address the proliferation of toxic content on social media, we introduce SMARTER, we introduce SMARTER, a data-efficient two-stage framework for explainable content moderation…

We propose a framework to modularize the training of neural language models that use diverse forms of sentence-external context (including metadata) by eliminating the need to jointly train sentence-external and within-sentence encoders.…

Large language models (LLMs) are increasingly strong contenders in machine translation. In this work, we focus on document-level translation, where some words cannot be translated without context from outside the sentence. Specifically, we…

Mining textual patterns in news, tweets, papers, and many other kinds of text corpora has been an active theme in text mining and NLP research. Previous studies adopt a dependency parsing-based pattern discovery approach. However, the…

Contextual Markov Decision Processes (CMDPs) offer a framework for sequential decision-making under external signals, but existing methods often fail to generalize in high-dimensional or unstructured contexts, resulting in excessive…