Most existing computational tools for assumption-based argumentation (ABA) focus on so-called flat frameworks, disregarding the more general case. In this paper, we study an instantiation-based approach for reasoning in possibly non-flat ABA. We make use of a semantics-preserving translation between ABA and bipolar argumentation frameworks (BAFs). By utilizing compilability theory, we establish that the constructed BAFs will in general be of exponential size. In order to keep the number of arguments and computational cost low, we present three ways of identifying redundant arguments. Moreover, we identify fragments of ABA which admit a poly-sized instantiation. We propose two algorithmic approaches for reasoning in possibly non-flat ABA. The first approach utilizes the BAF instantiation while the second works directly without constructing arguments. An empirical evaluation shows that the former outperforms the latter on many instances, reflecting the lower complexity of BAF reasoning. This result is in contrast to flat ABA, where direct approaches dominate instantiation-based approaches.

This study investigates why and how inconsistency in the generation of Large Language Models (LLMs) might induce or exacerbate societal injustice. For instance, LLMs frequently exhibit contrasting gender stereotypes regarding the same career depending on varied contexts, highlighting the arguably harmful unpredictability of LLMs' behavioral patterns. To augment the existing discrimination assessment with the capability to account for variation in LLM generation, we formulate the Prejudice-Volatility Framework (PVF) that precisely defines behavioral metrics for assessing LLMs, which delineate the probability distribution of LLMs' stereotypes from the perspective of token prediction probability. Specifically, we employ a data-mining approach to approximate the possible applied contexts of LLMs and devise statistical metrics to evaluate the corresponding contextualized societal discrimination risk. Further, we mathematically dissect the aggregated discrimination risk of LLMs into prejudice risk, originating from their system bias, and volatility risk, stemming from their generation inconsistency. While initially intended for assessing discrimination in LLMs, our proposed PVF facilitates the comprehensive and flexible measurement of any inductive biases, including knowledge alongside prejudice, across various modality models. We apply PVF to 12 most commonly adopted LLMs and compare their risk levels. Our findings reveal that: i) prejudice risk is the primary cause of discrimination risk in LLMs, indicating that inherent biases in these models lead to stereotypical outputs; ii) most LLMs exhibit significant pro-male stereotypes across nearly all careers; iii) alignment with Reinforcement Learning from Human Feedback lowers discrimination by reducing prejudice, but increases volatility; iv) discrimination risk in LLMs correlates with socio-economic factors like profession salaries.

Many populous countries including India are burdened with a considerable backlog of legal cases. Development of automated systems that could process legal documents and augment legal practitioners can mitigate this. However, there is a dearth of high-quality corpora that is needed to develop such data-driven systems. The problem gets even more pronounced in the case of low resource languages such as Hindi. In this resource paper, we introduce the Hindi Legal Documents Corpus (HLDC), a corpus of more than 900K legal documents in Hindi. Documents are cleaned and structured to enable the development of downstream applications. Further, as a use-case for the corpus, we introduce the task of bail prediction. We experiment with a battery of models and propose a Multi-Task Learning (MTL) based model for the same. MTL models use summarization as an auxiliary task along with bail prediction as the main task. Experiments with different models are indicative of the need for further research in this area. We release the corpus and model implementation code with this paper: https://github.com/Exploration-Lab/HLDC

The relation between (a fragment of) assumption-based argumentation (ABA) and logic programs (LPs) under stable model semantics is well-studied. However, for obtaining this relation, the ABA framework needs to be restricted to being flat, i.e., a fragment where the (defeasible) assumptions can never be entailed, only assumed to be true or false. Here, we remove this restriction and show a correspondence between non-flat ABA and LPs with negation as failure in their head. We then extend this result to so-called set-stable ABA semantics, originally defined for the fragment of non-flat ABA called bipolar ABA. We showcase how to define set-stable semantics for LPs with negation as failure in their head and show the correspondence to set-stable ABA semantics.

This study proposes two new dynamic assignment algorithms to match refugees and asylum seekers to geographic localities within a host country. The first, currently implemented in a multi-year randomized control trial in Switzerland, seeks to maximize the average predicted employment level (or any measured outcome of interest) of refugees through a minimum-discord online assignment algorithm. The performance of this algorithm is tested on real refugee resettlement data from both the US and Switzerland, where we find that it is able to achieve near-optimal expected employment compared to the hindsight-optimal solution, and is able to improve upon the status quo procedure by 40-50%. However, pure outcome maximization can result in a periodically imbalanced allocation to the localities over time, leading to implementation difficulties and an undesirable workflow for resettlement resources and agents. To address these problems, the second algorithm balances the goal of improving refugee outcomes with the desire for an even allocation over time. We find that this algorithm can achieve near-perfect balance over time with only a small loss in expected employment compared to the employment-maximizing algorithm. In addition, the allocation balancing algorithm offers a number of ancillary benefits compared to pure outcome maximization, including robustness to unknown arrival flows and greater exploration.

In the next few years, applications of Generative AI are expected to revolutionize a number of different areas, ranging from science & medicine to education. The potential for these seismic changes has triggered a lively debate about potential risks and resulted in calls for tighter regulation, in particular from some of the major tech companies who are leading in AI development. This regulation is likely to put at risk the budding field of open-source Generative AI. We argue for the responsible open sourcing of generative AI models in the near and medium term. To set the stage, we first introduce an AI openness taxonomy system and apply it to 40 current large language models. We then outline differential benefits and risks of open versus closed source AI and present potential risk mitigation, ranging from best practices to calls for technical and scientific contributions. We hope that this report will add a much needed missing voice to the current public discourse on near to mid-term AI safety and other societal impact.

Large Language Models (LLMs) can elicit unintended and even harmful content when misaligned with human values, posing severe risks to users and society. To mitigate these risks, current evaluation benchmarks predominantly employ expert-designed contextual scenarios to assess how well LLMs align with human values. However, the labor-intensive nature of these benchmarks limits their test scope, hindering their ability to generalize to the extensive variety of open-world use cases and identify rare but crucial long-tail risks. Additionally, these static tests fail to adapt to the rapid evolution of LLMs, making it hard to evaluate timely alignment issues. To address these challenges, we propose ALI-Agent, an evaluation framework that leverages the autonomous abilities of LLM-powered agents to conduct in-depth and adaptive alignment assessments. ALI-Agent operates through two principal stages: Emulation and Refinement. During the Emulation stage, ALI-Agent automates the generation of realistic test scenarios. In the Refinement stage, it iteratively refines the scenarios to probe long-tail risks. Specifically, ALI-Agent incorporates a memory module to guide test scenario generation, a tool-using module to reduce human labor in tasks such as evaluating feedback from target LLMs, and an action module to refine tests. Extensive experiments across three aspects of human values--stereotypes, morality, and legality--demonstrate that ALI-Agent, as a general evaluation framework, effectively identifies model misalignment. Systematic analysis also validates that the generated test scenarios represent meaningful use cases, as well as integrate enhanced measures to probe long-tail risks. Our code is available at https://github.com/SophieZheng998/ALI-Agent.git

Recent regulatory initiatives like the European AI Act and relevant voices in the Machine Learning (ML) community stress the need to describe datasets along several key dimensions for trustworthy AI, such as the provenance processes and social concerns. However, this information is typically presented as unstructured text in accompanying documentation, hampering their automated analysis and processing. In this work, we explore using large language models (LLM) and a set of prompting strategies to automatically extract these dimensions from documents and enrich the dataset description with them. Our approach could aid data publishers and practitioners in creating machine-readable documentation to improve the discoverability of their datasets, assess their compliance with current AI regulations, and improve the overall quality of ML models trained on them. In this paper, we evaluate the approach on 12 scientific dataset papers published in two scientific journals (Nature's Scientific Data and Elsevier's Data in Brief) using two different LLMs (GPT3.5 and Flan-UL2). Results show good accuracy with our prompt extraction strategies. Concrete results vary depending on the dimensions, but overall, GPT3.5 shows slightly better accuracy (81,21%) than FLAN-UL2 (69,13%) although it is more prone to hallucinations. We have released an open-source tool implementing our approach and a replication package, including the experiments' code and results, in an open-source repository.

Controlled Text Generation (CTG) aims to produce texts that exhibit specific desired attributes. In this study, we introduce a pluggable CTG framework for Large Language Models (LLMs) named Dynamic Attribute Graphs-based controlled text generation (DATG). This framework utilizes an attribute scorer to evaluate the attributes of sentences generated by LLMs and constructs dynamic attribute graphs. DATG modulates the occurrence of key attribute words and key anti-attribute words, achieving effective attribute control without compromising the original capabilities of the model. We conduct experiments across four datasets in two tasks: toxicity mitigation and sentiment transformation, employing five LLMs as foundational models. Our findings highlight a remarkable enhancement in control accuracy, achieving a peak improvement of 19.29% over baseline methods in the most favorable task across four datasets. Additionally, we observe a significant decrease in perplexity, markedly improving text fluency.

Systems based on machine learning may exhibit discriminatory behavior based on sensitive characteristics such as gender, sex, religion, or race. In light of this, various notions of fairness and methods to quantify discrimination were proposed, leading to the development of numerous approaches for constructing fair predictors. At the same time, imposing fairness constraints may decrease the utility of the decision-maker, highlighting a tension between fairness and utility. This tension is also recognized in legal frameworks, for instance in the disparate impact doctrine of Title VII of the Civil Rights Act of 1964 -- in which specific attention is given to considerations of business necessity -- possibly allowing the usage of proxy variables associated with the sensitive attribute in case a high-enough utility cannot be achieved without them. In this work, we analyze the tension between fairness and accuracy from a causal lens for the first time. We introduce the notion of a path-specific excess loss (PSEL) that captures how much the predictor's loss increases when a causal fairness constraint is enforced. We then show that the total excess loss (TEL), defined as the difference between the loss of predictor fair along all causal pathways vs. an unconstrained predictor, can be decomposed into a sum of more local PSELs. At the same time, enforcing a causal constraint often reduces the disparity between demographic groups. Thus, we introduce a quantity that summarizes the fairness-utility trade-off, called the causal fairness/utility ratio, defined as the ratio of the reduction in discrimination vs. the excess loss from constraining a causal pathway. This quantity is suitable for comparing the fairness-utility trade-off across causal pathways. Finally, as our approach requires causally-constrained fair predictors, we introduce a new neural approach for causally-constrained fair learning.