In this work, we broaden the investigation of admissibility notions in the context of assumption-based argumentation (ABA). More specifically, we study two prominent alternatives to the standard notion of admissibility from abstract argumentation, namely strong and weak admissibility, and introduce the respective preferred, complete and grounded semantics for general (sometimes called non-flat) ABA. To do so, we use abstract bipolar set-based argumentation frameworks (BSAFs) as formal playground since they concisely capture the relations between assumptions and are expressive enough to represent general non-flat ABA frameworks, as recently shown. While weak admissibility has been recently investigated for a restricted fragment of ABA in which assumptions cannot be derived (flat ABA), strong admissibility has not been investigated for ABA so far. We introduce strong admissibility for ABA and investigate desirable properties. We furthermore extend the recent investigations of weak admissibility in the flat ABA fragment to the non-flat case. We show that the central modularization property is maintained under classical, strong, and weak admissibility. We also show that strong and weakly admissible semantics in non-flat ABA share some of the shortcomings of standard admissible semantics and discuss ways to address these.

End-to-end visuomotor policies trained using behavior cloning have shown a remarkable ability to generate complex, multi-modal low-level robot behaviors. However, at deployment time, these policies still struggle to act reliably when faced with out-of-distribution (OOD) visuals induced by objects, backgrounds, or environment changes. Prior works in interactive imitation learning solicit corrective expert demonstrations under the OOD conditions -- but this can be costly and inefficient. We observe that task success under OOD conditions does not always warrant novel robot behaviors. In-distribution (ID) behaviors can directly be transferred to OOD conditions that share functional similarities with ID conditions. For example, behaviors trained to interact with in-distribution (ID) pens can apply to interacting with a visually-OOD pencil. The key challenge lies in disambiguating which ID observations functionally correspond to the OOD observation for the task at hand. We propose that an expert can provide this OOD-to-ID functional correspondence. Thus, instead of collecting new demonstrations and re-training at every OOD encounter, our method: (1) detects the need for feedback by first checking if current observations are OOD and then identifying whether the most similar training observations show divergent behaviors, (2) solicits functional correspondence feedback to disambiguate between those behaviors, and (3) intervenes on the OOD observations with the functionally corresponding ID observations to perform deployment-time generalization. We validate our method across diverse real-world robotic manipulation tasks with a Franka Panda robotic manipulator. Our results show that test-time functional correspondences can improve the generalization of a vision-based diffusion policy to OOD objects and environment conditions with low feedback.

Jailbreak attack can be used to access the vulnerabilities of Large Language Models (LLMs) by inducing LLMs to generate the harmful content. And the most common method of the attack is to construct semantically ambiguous prompts to confuse and mislead the LLMs. To access the security and reveal the intrinsic relation between the input prompt and the output for LLMs, the distribution of attention weight is introduced to analyze the underlying reasons. By using statistical analysis methods, some novel metrics are defined to better describe the distribution of attention weight, such as the Attention Intensity on Sensitive Words (Attn_SensWords), the Attention-based Contextual Dependency Score (Attn_DepScore) and Attention Dispersion Entropy (Attn_Entropy). By leveraging the distinct characteristics of these metrics, the beam search algorithm and inspired by the military strategy "Feint and Attack", an effective jailbreak attack strategy named as Attention-Based Attack (ABA) is proposed. In the ABA, nested attack prompts are employed to divert the attention distribution of the LLMs. In this manner, more harmless parts of the input can be used to attract the attention of the LLMs. In addition, motivated by ABA, an effective defense strategy called as Attention-Based Defense (ABD) is also put forward. Compared with ABA, the ABD can be used to enhance the robustness of LLMs by calibrating the attention distribution of the input prompt. Some comparative experiments have been given to demonstrate the effectiveness of ABA and ABD. Therefore, both ABA and ABD can be used to access the security of the LLMs. The comparative experiment results also give a logical explanation that the distribution of attention weight can bring great influence on the output for LLMs.

Artificial intelligence (AI) technologies are reshaping the way the legal industry operates. They are shifting focus from time-consuming and expensive workflows to efficient investigation of data and proactive ways to prevent emerging problems from spreading. More generally, use of AI is making legal services more accessible and providing lawyers with more powerful tools to find evidence and resolve cases in a fair and comprehensive way. AI is reshaping the way legal professionals gain fast and powerful insights into data to uncover evidence. As lawyers and other legal professionals continue to adopt AI for use in their everyday activities and workflows, they can extend their abilities far beyond what can be achieved today.

So far, advances in AI are not bringing us real "intelligence." Rather, these advances are bringing us a key part of intelligence: prediction. This enables businesses to make predictions faster and more precisely to improve their business models and marketplace advantage. In this episode of Mind the Gap, Avi Goldfarb, an economist at the University of Toronto's Rotman School of Management and one of the authors of "Prediction Machines: The Simple Economics of Artificial Intelligence," will explain the economics of AI and how it can lead to better and cheaper predictions.

We present a novel approach to account for preferences in a well known structured argumentation formalism, Assumption-Based Argumentation (ABA). The new formalism, called ABA, incorporates object-level preferences (over assumptions) directly into the attack relation to reverse attacks. We give several basic desirable properties of ABA .

Assumption-based argumentation (ABA) is a central structured argumentation formalism. As shown recently, answer set programming (ASP) enables efficiently solving NP-hard reasoning tasks of ABA in practice, in particular in the commonly studied logic programming fragment of ABA. In this work, we harness recent advances in incremental ASP solving for developing effective algorithms for reasoning tasks in the logic programming fragment of ABA that are presumably hard for the second level of the polynomial hierarchy, including skeptical reasoning under preferred semantics as well as preferential reasoning. In particular, we develop non-trivial counterexample-guided abstraction refinement procedures based on incremental ASP solving for these tasks. We also show empirically that the procedures are significantly more effective than previously proposed algorithms for the tasks. This paper is under consideration for acceptance in TPLP.

As banks move to responsibly integrate artificial intelligence and machine learning capabilities into their business processes, the American Bankers Association this week urged regulators to focus on providing greater clarity around the use of AI and ensuring that there is a consistent regulatory standard for its use across all financial services providers. In a letter responding to a recent request for information on AI and machine learning, ABA emphasized that given the stringent supervision and regulation banks are already subject to, "new banking regulations are not necessary or warranted to address AI." Rather, regulators should focus their efforts on clarifying existing regulations and guidance to address AI-related risks and ensure that banks can continue to innovate in a safe, responsible manner, ABA said. Among other things, ABA specifically called for additional guidance around fair lending risk in the use of AI, and how banks should be managing disparate impact risks. The association also emphasized the need for coordination across the regulatory agencies on the issuance of any AI-related guidance, and encouraged the agencies to support voluntary pilot or innovation programs that banks may choose to participate in. "AI makes banking services better, cheaper, and more widely available, and will continue to do so. While these benefits do not come without risks, we believe that the robust bank regulatory structure already captures these risks today," the association said.

As banks move to responsibly integrate artificial intelligence and machine learning capabilities into their business processes, the American Bankers …

We investigate properties of ABA+, a formalism that extends the well studied structured argumentation formalism Assumption-Based Argumentation (ABA) with a preference handling mechanism. In particular, we establish desirable properties that ABA+ semantics exhibit. These pave way to the satisfaction by ABA+ of some (arguably) desirable principles of preference handling in argumentation and nonmonotonic reasoning, as well as non-monotonic inference properties of ABA+ under various semantics.