Related papers: Steering Llama 2 via Contrastive Activation Additi…

Research demonstrates that the proactivity of in-vehicle conversational assistants (IVCAs) can help to reduce distractions and enhance driving safety, better meeting users' cognitive needs. However, existing IVCAs struggle with user intent…

Understanding and controlling the behavior of large language models (LLMs) is an increasingly important topic in multilingual NLP. Beyond prompting or fine-tuning, , i.e.,~manipulating internal representations during inference, has emerged…

With the rapid advancement of Vision Language Models (VLMs), refusal mechanisms have become a critical component for ensuring responsible and safe model behavior. However, existing refusal strategies are largely \textit{one-size-fits-all}…

Cross-lingual aspect-based sentiment analysis (ABSA) involves detailed sentiment analysis in a target language by transferring knowledge from a source language with available annotated data. Most existing methods depend heavily on often…

Multi-agent debate has been shown to improve reasoning in large language models (LLMs). However, it is compute-intensive, requiring generation of long transcripts before answering questions. To address this inefficiency, we develop a…

Chain-of-thought (CoT) prompting has been extended to large audio-language models (LALMs) to elicit reasoning, yet enhancing its effectiveness without training remains challenging. We study inference-time model steering as a training-free…

Large language models (LLMs) have demonstrated impressive capabilities in natural language understanding and generation, but controlling their behavior reliably remains challenging, especially in open-ended generation settings. This paper…

This study sheds light on the imperative need to bolster safety and privacy measures in large language models (LLMs), such as GPT-4 and LLaMA-2, by identifying and mitigating their vulnerabilities through explainable analysis of prompt…

Deploying LLMs in real-world applications requires controllable output that satisfies multiple desiderata at the same time. While existing work extensively addresses LLM steering for a single behavior, \textit{compositional steering} --…

Sparse autoencoders (SAEs) have recently emerged as a powerful tool for language model steering. Prior work has explored top-k SAE latents for steering, but we observe that many dimensions among the top-k latents capture non-semantic…

As AI Agents based on Large Language Models (LLMs) have shown potential in practical applications across various fields, how to quickly deploy an AI agent and how to conveniently expand the application scenario of AI agents has become a…

Achieving pronunciation proficiency in a second language (L2) remains a challenge, despite the development of Computer-Assisted Pronunciation Training (CAPT) systems. Traditional CAPT systems often provide unintuitive feedback that lacks…

Vision-Language-Action (VLA) models are emerging as a promising paradigm for end-to-end autonomous driving, valued for their potential to leverage world knowledge and reason about complex driving scenes. However, existing methods suffer…

Steering vectors are a promising approach to aligning language model behavior at inference time. In this paper, we propose a framework to assess the limitations of steering vectors as alignment mechanisms. Using a framework of transformer…

In this paper, we conduct an emulation-guided study to systematically investigate the feasibility of Large language model (LLM)-driven congestion control. The exploration is structured into two phases. The first phase derisks the whole…

The broad capabilities of Language Models (LMs) can be limited by their sensitivity to distractor tasks: LMs can infer secondary tasks from the prompt in addition to the intended one, leading to unwanted outputs. For example, prompt…

Recent advancements in large language models (LLMs) have resulted in increasingly anthropomorphic language concerning the ability of LLMs to reason. Whether reasoning in LLMs should be understood to be inherently different is, however,…

Alignment in LLMs is more brittle than commonly assumed: misalignment can be triggered by adversarial prompts, benign fine-tuning, emergent misalignment, and goal misgeneralization. Recent evidence suggests that some misalignment behaviors…

Large Language Models (LLMs) hold immense potential to generate synthetic data of high quality and utility, which has numerous applications from downstream model training to practical data utilisation. However, contemporary models, despite…

Inference-time LLM alignment methods, particularly activation steering, offer an alternative to fine-tuning by directly modifying activations during generation. Existing methods, however, often rely on non-anticipative interventions that…