Related papers: Steering Without Side Effects: Improving Post-Depl…

Despite the success of Instruction Tuning (IT) in training large language models (LLMs), such models often leverage spurious or biased features learnt from their training data and can become misaligned, leading to undesired behaviours.…

Steering vectors are a lightweight method to control language model behavior by adding a learned bias to the activations at inference time. Although steering demonstrates promising performance, recent work shows that it can be unreliable or…

Multilingual Large Language Models (LLMs) often exhibit hallucinations such as unintended code-switching, reducing reliability in downstream tasks. We propose latent-space language steering, a lightweight inference-time method that…

Although large language models (LLMs) demonstrate impressive proficiency in various tasks, they present potential safety risks, such as `jailbreaks', where malicious inputs can coerce LLMs into generating harmful content bypassing safety…

Large language models (LLMs) are shown to be vulnerable to jailbreaking attacks where adversarial prompts are designed to elicit harmful responses. While existing defenses effectively mitigate single-turn attacks by detecting and filtering…

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…

Large language model (LLM) safety is a critical issue, with numerous studies employing red team testing to enhance model security. Among these, jailbreak methods explore potential vulnerabilities by crafting malicious prompts that induce…

Large language models (LLMs) achieve remarkable advancements by leveraging tools to interact with environments, a critical step toward generalized AI. However, the standard supervised fine-tuning (SFT) approach, which relies on large-scale…

Large language models (LLMs) increasingly serve as automated evaluators, yet they suffer from "self-preference bias": a tendency to favor their own outputs over those of other models. This bias undermines fairness and reliability in…

Activation steering is a method for controlling Large Language Model (LLM) behavior by intervening in its internal representations to increase the alignment with a specific target feature direction. However, standard interventions, such as…

Text generation has a fundamental limitation almost by definition: there is no taking back tokens that have been generated, even when they are clearly problematic. In the context of language model safety, when a partial unsafe generation is…

Changing the behavior of large language models (LLMs) can be as straightforward as editing the Transformer's residual streams using appropriately constructed "steering vectors." These modifications to internal neural activations, a form of…

Knowledge Tracing (KT) is a critical task in online learning for modeling student knowledge over time. Despite the success of deep learning-based KT models, which rely on sequences of numbers as data, most existing approaches fail to…

We present a novel approach to bias mitigation in large language models (LLMs) by applying steering vectors to modify model activations in forward passes. We compute 8 steering vectors, each corresponding to a different social bias axis,…

We introduce Refusal Steering, an inference-time method to exercise fine-grained control over Large Language Models refusal behaviour on politically sensitive topics without retraining. We replace fragile pattern-based refusal detection…

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…

Large Language Model (LLM) alignment remains vulnerable to jailbreak attacks that elicit unsafe responses, motivating pre-model and post-model guards. Pre-model guards audit the safety of prompts before invoking target models. However,…

Zero-shot Text-to-Speech (TTS) models can generate speech that captures both the voice timbre and accent of a reference speaker. However, disentangling these attributes remains challenging, as the output often inherits both the accent and…

We have uncovered a powerful jailbreak technique that leverages large language models' ability to diverge from prior context, enabling them to bypass safety constraints and generate harmful outputs. By simply instructing the LLM to deviate…

While large language models (LLMs) have seen unprecedented advancements in capabilities and applications across a variety of use-cases, safety alignment of these models is still an area of active research. The fragile nature of LLMs, even…