相关论文: REAL: Reading Out Transformer Activations for Prec…

Aligning Large Language Models (LLMs) with specific personas typically relies on expensive and monolithic Supervised Fine-Tuning (SFT) or RLHF. While effective, these methods require training distinct models for every target personality…

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} --…

We present the LM Transparency Tool (LM-TT), an open-source interactive toolkit for analyzing the internal workings of Transformer-based language models. Differently from previously existing tools that focus on isolated parts of the…

Large Language Models (LLMs) are important tools for reasoning and problem-solving, while they often operate passively, answering questions without actively discovering new ones. This limitation reduces their ability to simulate human-like…

The influence of personas on Large Language Models (LLMs) has been widely studied, yet their direct impact on performance remains uncertain. This work explores a novel approach to guiding LLM behaviour through role vectors, an alternative…

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.…

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…

We investigate the internal behavior of Transformer-based Large Language Models (LLMs) when they generate factually incorrect text. We propose modeling factual queries as constraint satisfaction problems and use this framework to…

A major challenge for the operation of large language models (LLMs) is how to predict whether a specific LLM will produce sufficiently high-quality output for a given query. Existing approaches rely on external classifiers, most commonly…

Large language models (LLMs) have demonstrated remarkable performance across various real-world tasks. However, they often struggle to fully comprehend and effectively utilize their input contexts, resulting in responses that are unfaithful…

Discrete Diffusion Language Models (DLMs) offer a promising non-autoregressive alternative for text generation, yet effective mechanisms for inference-time control remain relatively underexplored. Existing approaches include sampling-level…

Inference-time steering methods offer a lightweight alternative to fine-tuning large language models (LLMs) and vision-language models (VLMs) by modifying internal activations at test time without updating model weights. However, most…

Large language model (LLM) steering has emerged as a promising paradigm for controlling model behavior at inference time through targeted manipulation of hidden states, offering a lightweight alternative to expensive retraining. However,…

Recent Vision-Language-Action (VLA) models show strong generalization capabilities, yet they lack introspective mechanisms for anticipating failures and requesting help from a human supervisor. We present \textbf{INSIGHT}, a learning…

Multimodal Emotion Recognition (MER) is critical for interpreting real-world interactions. While Multimodal Large Language Models (MLLM) have shown promise in MER, their internal decision-making mechanisms under modality conflict and…

Large Language Models (LLMs) are increasingly integrated into diverse applications. The rapid evolution of LLMs presents opportunities for developers to enhance applications continuously. However, this constant adaptation can also lead to…

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…

Time series data measure how environments change over time and drive decision-making in critical domains like finance and healthcare. A common goal in analyzing time series data is to understand the underlying events that cause the observed…

Large language models often generate factually incorrect outputs, motivating efforts to detect the truthfulness of their content. Most existing approaches rely on training probes over internal activations, but these methods suffer from…

Recent advancements in language models (LMs) have marked a shift toward the growing importance of post-training. Yet, post-training approaches such as supervised fine-tuning (SFT) do not guarantee the effective use of knowledge acquired…