相关论文: Value Alignment Tax: Measuring Value Trade-offs in…

Reinforcement learning with verifiable rewards (RLVR) is a practical, scalable way to improve large language models on math, code, and other structured tasks. However, we argue that many headline RLVR gains are not yet well validated…

We analyse multi-purpose audio using tools to visualise similarities within the data that may be observed via unsupervised methods. The success of machine learning classifiers is affected by the information contained within system inputs,…

Linear relations, containing measurement errors in input and output data, are considered. Parameters of these so-called errors-in-variables models can change at some unknown moment. The aim is to test whether such an unknown change has…

As large language models (LLMs) become integral to intelligent user interfaces (IUIs), their role as decision-making agents raises critical concerns about alignment. Although extensive research has addressed issues such as factuality, bias,…

Value adjustment of uncollateralized trades is determined within a risk-neutral pricing framework. When hedging such trades, investors cannot freely trade protection on their own name, thus facing an incomplete market. This fact is…

Reinforcement learning (RL) has shown impressive results in sequential decision-making tasks. Meanwhile, Large Language Models (LLMs) and Vision-Language Models (VLMs) have emerged, exhibiting impressive capabilities in multimodal…

As LLMs become increasingly integrated into human society, evaluating their orientations on human values from social science has drawn growing attention. Nevertheless, it is still unclear why human values matter for LLMs, especially in…

Multi-task learning (MTL) aims to build general-purpose vision systems by training a single network to perform multiple tasks jointly. While promising, its potential is often hindered by "unbalanced optimization", where task interference…

Aligning Large Language Models (LLMs) with the diverse spectrum of human values remains a central challenge: preference-based methods often fail to capture deeper motivational principles. Value-based approaches offer a more principled path,…

Recent advances in Large Language Models (LLMs) have sparked wide interest in validating and comprehending the human-like cognitive-behavioral traits LLMs may capture and convey. These cognitive-behavioral traits include typically…

There is a growing interest in training domain-expert LLMs that excel in specific technical fields compared to their general-purpose instruction-tuned counterparts. However, these expert models often experience a loss in their safety…

Prior work in multi-objective reinforcement learning typically uses linear reward scalarization with fixed weights, which provably fails to capture non-convex Pareto fronts and thus yields suboptimal results. This limitation becomes…

Reinforcement learning (RL) has become the de facto standard practice for sequential decision-making problems by improving future acting policies with feedback. However, RL algorithms may require extensive trial-and-error interactions to…

Although Large Language Models (LLMs) achieve strong alignment through supervised fine-tuning and reinforcement learning from human feedback, the alignment is often fragile under subsequent fine-tuning. Existing explanations either…

In this paper, we propose an online-matching-based model to study the assignment problems arising in a wide range of online-matching markets, including online recommendations, ride-hailing platforms, and crowdsourcing markets. It features…

Growing use of machine learning in policy and social impact settings have raised concerns for fairness implications, especially for racial minorities. These concerns have generated considerable interest among machine learning and artificial…

As AI systems become more advanced, ensuring their alignment with a diverse range of individuals and societal values becomes increasingly critical. But how can we capture fundamental human values and assess the degree to which AI systems…

Modern AI systems increasingly rely on workflows composed of multiple interacting agents, some powered by large language models (LLMs) and others by conventional computational modules. This paper analyzes the fundamental tradeoffs between…

In computing, as in many aspects of life, changes incur cost. Many optimization problems are formulated as a one-time instance starting from scratch. However, a common case that arises is when we already have a set of prior assignments, and…

With the success of pre-trained visual-language (VL) models such as CLIP in visual representation tasks, transferring pre-trained models to downstream tasks has become a crucial paradigm. Recently, the prompt tuning paradigm, which draws…