Silenced Biases: The Dark Side LLMs Learned to Refuse

Safety-aligned large language models (LLMs) are becoming increasingly widespread, especially in sensitive applications where fairness is essential and biased outputs can cause significant harm. However, evaluating the fairness of models is a complex challenge, and approaches that do so typically utilize standard question-answer (QA) styled schemes. Such methods often overlook deeper issues by interpreting the model's refusal responses as positive fairness measurements, which creates a false sense of fairness. In this work, we introduce the concept of silenced biases, which are unfair preferences encoded within models' latent space and are effectively concealed by safety-alignment. Previous approaches that considered similar indirect biases often relied on prompt manipulation or handcrafted implicit queries, which present limited scalability and risk contaminating the evaluation process with additional biases. We propose the Silenced Bias Benchmark (SBB), which aims to uncover these biases by employing activation steering to reduce model refusals during QA. SBB supports easy expansion to new demographic groups and subjects, presenting a fairness evaluation framework that encourages the future development of fair models and tools beyond the masking effects of alignment training. We demonstrate our approach over multiple LLMs, where our findings expose an alarming distinction between models' direct responses and their underlying fairness issues.

Causal DAG Summarization (Full Version)

Causal inference aids researchers in discovering cause-and-effect relationships, leading to scientific insights. Accurate causal estimation requires identifying confounding variables to avoid false discoveries. Pearl's causal model uses causal DAGs to identify confounding variables, but incorrect DAGs can lead to unreliable causal conclusions. However, for high dimensional data, the causal DAGs are often complex beyond human verifiability. Graph summarization is a logical next step, but current methods for general-purpose graph summarization are inadequate for causal DAG summarization. This paper addresses these challenges by proposing a causal graph summarization objective that balances graph simplification for better understanding while retaining essential causal information for reliable inference. We develop an efficient greedy algorithm and show that summary causal DAGs can be directly used for inference and are more robust to misspecification of assumptions, enhancing robustness for causal inference. Experimenting with six real-life datasets, we compared our algorithm to three existing solutions, showing its effectiveness in handling high-dimensional data and its ability to generate summary DAGs that ensure both reliable causal inference and robustness against misspecifications.

Guided Exploration of Data Summaries

Data summarization is the process of producing interpretable and representative subsets of an input dataset. It is usually performed following a one-shot process with the purpose of finding the best summary. A useful summary contains k individually uniform sets that are collectively diverse to be representative. Uniformity addresses interpretability and diversity addresses representativity. Finding such as summary is a difficult task when data is highly diverse and large. We examine the applicability of Exploratory Data Analysis (EDA) to data summarization and formalize Eda4Sum, the problem of guided exploration of data summaries that seeks to sequentially produce connected summaries with the goal of maximizing their cumulative utility. EdA4Sum generalizes one-shot summarization. We propose to solve it with one of two approaches: (i) Top1Sum which chooses the most useful summary at each step; (ii) RLSum which trains a policy with Deep Reinforcement Learning that rewards an agent for finding a diverse and new collection of uniform sets at each step. We compare these approaches with one-shot summarization and top-performing EDA solutions. We run extensive experiments on three large datasets. Our results demonstrate the superiority of our approaches for summarizing very large data, and the need to provide guidance to domain experts.

Algorithmic Rewriting of Health-Related Ads to Improve their Performance

Search advertising is one of the most commonly-used methods of advertising. Past work has shown that search advertising can be employed to improve health by eliciting positive behavioral change. However, writing effective advertisements requires expertise and (possible expensive) experimentation, both of which may not be available to public health authorities wishing to elicit such behavioral changes, especially when dealing with a public health crises such as epidemic outbreaks. Here we develop an algorithm which builds on past advertising data to train a sequence-to-sequence Deep Neural Network which "translates" advertisements into optimized ads that are more likely to be clicked. The network is trained using more than 114 thousands ads shown on Microsoft Advertising. We apply this translator to two health related domains: Medical Symptoms (MS) and Preventative Healthcare (PH) and measure the improvements in click-through rates (CTR). Our experiments show that the generated ads are predicted to have higher CTR in 81% of MS ads and 76% of PH ads. To understand the differences between the generated ads and the original ones we develop estimators for the affective attributes of the ads. We show that the generated ads contain more calls-to-action and that they reflect higher valence (36% increase) and higher arousal (87%) on a sample of 1000 ads. Finally, we run an advertising campaign where 10 random ads and their rephrased versions from each of the domains are run in parallel. We show an average improvement in CTR of 68% for the generated ads compared to the original ads. Our results demonstrate the ability to automatically optimize advertisement for the health domain. We believe that our work offers health authorities an improved ability to help nudge people towards healthier behaviors while saving the time and cost needed to optimize advertising campaigns.