Related papers: Inference Time Causal Probing in LLMs
In recent years, discriminative self-supervised methods have made significant strides in advancing various visual tasks. The central idea of learning a data encoder that is robust to data distortions/augmentations is straightforward yet…
Reasoning is an important task for large language models (LLMs). Among all the reasoning paradigms, inductive reasoning is one of the fundamental types, which is characterized by its particular-to-general thinking process and the…
With the success of self-supervised representations, researchers seek a better understanding of the information encapsulated within a representation. Among various interpretability methods, we focus on classification-based linear probing.…
Large Language Models (LLMs) excel at few-shot learning via in-context learning (ICL). However, the effectiveness of ICL is often sensitive to the selection and ordering of demonstration examples. To address this, we present MarginSel:…
Causal influence measures for machine learnt classifiers shed light on the reasons behind classification, and aid in identifying influential input features and revealing their biases. However, such analyses involve evaluating the classifier…
Dynamic Causal Modeling (DCM) is a Bayesian framework for inferring on hidden (latent) neuronal states, based on measurements of brain activity. Since its introduction in 2003 for functional magnetic resonance imaging data, DCM has been…
Text-to-image diffusion models exhibit remarkable generative capabilities, yet their internal operations remain opaque, particularly when handling prompts that are not fully descriptive. In such scenarios, models must make implicit…
There are two primary ways of incorporating new information into a language model (LM): changing its prompt or changing its parameters, e.g. via fine-tuning. Parameter updates incur no long-term storage cost for model changes. However, for…
Large Vision-Language Models (LVLMs) often suffer from object hallucination, making erroneous judgments about the presence of objects in images. We propose this primar- ily stems from spurious correlations arising when models strongly…
Large Language Models (LLMs) have shown impressive potential to simulate human behavior. We identify a fundamental challenge in using them to simulate experiments: when LLM-simulated subjects are blind to the experimental design (as is…
Vision-language foundation models (VLMs) have shown great potential in feature transfer and generalization across a wide spectrum of medical-related downstream tasks. However, fine-tuning these models is resource-intensive due to their…
We propose cognitive prompting as a novel approach to guide problem-solving in large language models (LLMs) through structured, human-like cognitive operations, such as goal clarification, decomposition, filtering, abstraction, and pattern…
Steering large language models (LLMs) is usually done by either instruction prompting or activation steering. Prompting often gives strong control, but caches guidance tokens at every layer and can clutter long interactions; activation…
A critical challenge for reinforcement learning (RL) is making decisions based on incomplete and noisy observations, especially in perturbed and partially observable Markov decision processes (P$^2$OMDPs). Existing methods fail to mitigate…
Detecting video moments and highlights from natural-language queries have been unified by transformer-based methods. Other works use generative Multimodal LLM (MLLM) to predict moments and/or highlights as text timestamps, utilizing its…
Solving constraints involving inductive (aka recursive) definitions is challenging. State-of-the-art SMT/CHC solvers and first-order logic provers provide only limited support for solving such constraints, especially when they involve,…
Self-attention is usually described as a flexible, content-adaptive way to mix a token with information from its past. We reinterpret causal self-attention transformers, the backbone of modern foundation models, within a probabilistic…
LLMs are increasingly embedded in everyday decision-making, yet their outputs can encode subtle, unintended behaviours that shape user beliefs and actions. We refer to these covert, goal-directed behaviours as hidden intentions, which may…
Large language models (LLMs) frequently hallucinate and produce factual errors, yet our understanding of why they make these errors remains limited. In this study, we delve into the underlying mechanisms of LLM hallucinations from the…
We introduce and study artificial impressions--patterns in LLMs' internal representations of prompts that resemble human impressions and stereotypes based on language. We fit linear probes on generated prompts to predict impressions…