Related papers: Whispering Experts: Neural Interventions for Toxic…

Large language models (LLMs) are now ubiquitous in user-facing applications, yet they still generate undesirable toxic outputs, including profanity, vulgarity, and derogatory remarks. Although numerous detoxification methods exist, most…

Reward models (RMs) play a central role in aligning large language models (LLMs) with human preferences. However, RMs are often sensitive to spurious features such as response length. Existing inference-time approaches for mitigating these…

Large language models (LLMs) have enabled agents to perform complex reasoning and decision-making through free-form language interactions. However, in open-ended language action environments (e.g., negotiation or question-asking games), the…

Unsupervised automatic readability assessment (ARA) methods have important practical and research applications (e.g., ensuring medical or educational materials are suitable for their target audiences). In this paper, we propose a new…

Conventional online surveys provide limited personalization, often resulting in low engagement and superficial responses. Although AI survey chatbots improve convenience, most are still reactive: they rely on fixed dialogue trees or static…

Modern Large Language Models (LLMs) are excellent at generating synthetic data. However, their performance in sensitive domains such as text detoxification has not received proper attention from the scientific community. This paper explores…

Contextual priming, where earlier stimuli covertly bias later judgments, offers an unexplored attack surface for large language models (LLMs). We uncover a contextual priming vulnerability in which the previous response in the dialogue can…

The dissemination of Large Language Models (LLMs), trained at scale, and endowed with powerful text-generating abilities, has made it easier for all to produce harmful, toxic, faked or forged content. In response, various proposals have…

We propose Sensitivity-Uncertainty Alignment (SUA), a framework for analyzing failures of large language models under adversarial and ambiguous inputs. We argue that adversarial sensitivity and ambiguity reflect a common issue: misalignment…

Language-specific neurons in LLMs that strongly correlate with individual languages have been shown to influence model behavior by deactivating them. However, their role in amplification remains underexplored. This work investigates the…

Neural language models (NLM) have been shown to outperform conventional n-gram language models by a substantial margin in Automatic Speech Recognition (ASR) and other tasks. There are, however, a number of challenges that need to be…

Low-Rank Adaptation (LoRA) is a widely adopted parameter-efficient fine-tuning (PEFT) method validated across NLP and CV domains. However, LoRA faces an inherent low-rank bottleneck: narrowing its performance gap with full finetuning…

Large language models (LLMs) can elicit social bias during generations, especially when inference with toxic prompts. Controlling the sensitive attributes in generation encounters challenges in data distribution, generalizability, and…

Transformer-based language models are able to generate fluent text and be efficiently adapted across various natural language generation tasks. However, language models that are pretrained on large unlabeled web text corpora have been shown…

Large language models (LLMs) exhibit remarkable capabilities in natural language processing but face catastrophic forgetting when learning new tasks, where adaptation to a new domain leads to a substantial decline in performance on previous…

The volume of machine-generated content online has grown dramatically due to the widespread use of Large Language Models (LLMs), leading to new challenges for content moderation systems. Conventional content moderation classifiers, which…

Recent years have witnessed significant progress in multilingual automatic speech recognition (ASR), driven by the emergence of end-to-end (E2E) models and the scaling of multilingual datasets. Despite that, two main challenges persist in…

Language agents powered by large language models (LLMs) have demonstrated remarkable capabilities in understanding, reasoning, and executing complex tasks. However, developing robust agents presents significant challenges: substantial…

When trained on large, unfiltered crawls from the internet, language models pick up and reproduce all kinds of undesirable biases that can be found in the data: they often generate racist, sexist, violent or otherwise toxic language. As…

Generative language models have improved drastically, and can now produce realistic text outputs that are difficult to distinguish from human-written content. For malicious actors, these language models bring the promise of automating the…