相关论文: Why Don't Prompt-Based Fairness Metrics Correlate?

Accurately predicting mortality risk in intensive care unit (ICU) patients is essential for clinical decision-making. Although large language models (LLMs) show strong potential in structured medical prediction tasks, their outputs may…

The wording of natural language prompts has been shown to influence the performance of large language models (LLMs), yet the role of politeness and tone remains underexplored. In this study, we investigate how varying levels of prompt…

Large Language Models (LLMs) are increasingly deployed in socially sensitive settings, raising concerns about fairness and biases, particularly across intersectional demographic attributes. In this paper, we systematically evaluate…

This work takes a critical stance on previous studies concerning fairness evaluation in Large Language Model (LLM)-based recommender systems, which have primarily assessed consumer fairness by comparing recommendation lists generated with…

Vision-language models enable open-vocabulary object grounding through natural language queries, under the implicit assumption that semantically equivalent descriptions yield consistent outputs. We examine this assumption using a controlled…

Fine-tuning continuous prompts for target tasks has recently emerged as a compact alternative to full model fine-tuning. Motivated by these promising results, we investigate the feasibility of extracting a discrete (textual) interpretation…

Reinforcement learning with verifiable rewards has driven recent advances in LLM post-training, in particular for reasoning. Policy optimization algorithms generate a number of responses for a given prompt and then effectively weight the…

Ranked lists are frequently used by information retrieval (IR) systems to present results believed to be relevant to the users information need. Fairness is a relatively new but important aspect of these rankings to measure, joining a rich…

Recently, object counting has shifted towards class-agnostic counting (CAC), which counts instances of arbitrary object classes never seen during model training. With advancements in robust vision-and-language foundation models, there is a…

Large language model performance can be improved in a large number of ways. Many such techniques, like fine-tuning or advanced tool usage, are time-intensive and expensive. Although prompt engineering is significantly cheaper and often…

Natural Language Processing (NLP) systems learn harmful societal biases that cause them to amplify inequality as they are deployed in more and more situations. To guide efforts at debiasing these systems, the NLP community relies on a…

Online dating platforms have fundamentally transformed the formation of romantic relationships, with millions of users worldwide relying on algorithmic matching systems to find compatible partners. However, current recommendation systems in…

As machine learning algorithms grow in popularity and diversify to many industries, ethical and legal concerns regarding their fairness have become increasingly relevant. We explore the problem of algorithmic fairness, taking an…

Weak supervision enables efficient development of training sets by reducing the need for ground truth labels. However, the techniques that make weak supervision attractive -- such as integrating any source of signal to estimate unknown…

Background: The wide adoption of AI- and ML-based systems in sensitive domains raises severe concerns about their fairness. Many methods have been proposed in the literature to enhance software fairness. However, the majority behave as a…

Direct alignment methods are increasingly used to align large language models (LLMs) with human preferences. However, many real-world alignment problems involve multiple conflicting objectives, where naive aggregation of preferences can…

Reward-model-based fine-tuning is a central paradigm in aligning Large Language Models with human preferences. However, such approaches critically rely on the assumption that proxy reward models accurately reflect intended supervision, a…

One of the goals of fairness research in NLP is to measure and mitigate stereotypical biases that are propagated by NLP systems. However, such work tends to focus on single axes of bias (most often gender) and the English language.…

In the realm of multi-objective alignment for large language models, balancing disparate human preferences often manifests as a zero-sum conflict. Specifically, the intrinsic tension between competing goals dictates that aggressively…

Despite the increasing effectiveness of language models, their reasoning capabilities remain underdeveloped. In particular, causal reasoning through counterfactual question answering is lacking. This work aims to bridge this gap. We first…