Related papers: ALM-MTA:Front-Door Causal Multi-Touch Attribution …

The reward model (RM) plays a crucial role in aligning Large Language Models (LLMs) with human preferences through Reinforcement Learning, where the Bradley-Terry (BT) objective has been recognized as simple yet powerful, specifically for…

Federated Prompt Tuning (FPT) is an efficient method for cross-client collaborative fine-tuning of large Vision-Language Models (VLMs). However, models tuned using FPT are vulnerable to adversarial attacks, leading to misclassification in…

Online multi-task learning (OMTL) enhances streaming data processing by leveraging the inherent relations among multiple tasks. It can be described as an optimization problem in which a single loss function is defined for multiple tasks.…

As the representation capability of Pre-trained Language Models (PLMs) improve, there is growing concern that they will inherit social biases from unprocessed corpora. Most previous debiasing techniques used Counterfactual Data Augmentation…

Large Language Models (LLMs), such as GPT-4 and Llama, have demonstrated remarkable abilities in generating natural language. However, they also pose security and integrity challenges. Existing countermeasures primarily focus on…

Marketers employ various online advertising channels to reach customers, and they are particularly interested in attribution for measuring the degree to which individual touchpoints contribute to an eventual conversion. The availability of…

Large language models (LLMs) can simulate human-like reasoning and decision-making in individual agents. LLM-powered multi-agent systems (MAS) combine such agents to simulate population-scale social phenomena such as polarization,…

When deploying artificial agents in real-world environments where they interact with humans, it is crucial that their behavior is aligned with the values, social norms or other requirements of that environment. However, many environments…

Real-world domain experts (e.g., doctors) rarely annotate only a decision label in their day-to-day workflow without providing explanations. Yet, existing low-resource learning techniques, such as Active Learning (AL), that aim to support…

Recent LLMs have enabled significant advancements for conversational agents. However, they are also well known to hallucinate, producing responses that seem plausible but are factually incorrect. On the other hand, users tend to over-rely…

The autonomous driving community is increasingly focused on addressing corner case problems, particularly those related to ensuring driving safety under adverse conditions (e.g., nighttime, fog, rain). To this end, the task of Adverse…

Foundation models for vision have transformed visual recognition with powerful pretrained representations and strong zero-shot capabilities, yet their potential for data-efficient learning remains largely untapped. Active Learning (AL) aims…

Reward modeling is essential for aligning Large Language Models(LLMs) with human preferences, yet conventional reward models suffer from poor interpretability and heavy reliance on costly expert annotations. While recent rubric-based…

Optimization-based adversarial suffixes can jailbreak aligned large language models (LLMs) while remaining fluent, weakening static and windowed perplexity-based detectors. We cast adversarial suffix detection as an online change-point…

The great success of Transformer-based models benefits from the powerful multi-head self-attention mechanism, which learns token dependencies and encodes contextual information from the input. Prior work strives to attribute model decisions…

Test-Time Adaptation (TTA) enables pre-trained models to bridge the gap between source and target datasets using unlabeled test data, addressing domain shifts caused by corruptions like weather changes, noise, or sensor malfunctions in test…

We present the ADaptive Adversarial Imitation Learning (ADAIL) algorithm for learning adaptive policies that can be transferred between environments of varying dynamics, by imitating a small number of demonstrations collected from a single…

Reliable models should not only predict correctly, but also justify decisions with acceptable evidence. Yet conventional supervised learning typically provides only class-level labels, allowing models to achieve high accuracy through…

Multi-Task Learning (MTL) is designed to train multiple correlated tasks simultaneously, thereby enhancing the performance of individual tasks. Typically, a multi-task network structure consists of a shared backbone and task-specific…

Fine-tuning large pre-trained language models on downstream tasks is apt to suffer from overfitting when limited training data is available. While dropout proves to be an effective antidote by randomly dropping a proportion of units,…