Jasmina Gajcin

Jasmina Gajcin, Ivana Dusparic

While AI algorithms have shown remarkable success in various fields, their lack of transparency hinders their application to real-life tasks. Although explanations targeted at non-experts are necessary for user trust and human-AI collaboration, the majority of explanation methods for AI are focused on developers and expert users. Counterfactual explanations are local explanations that offer users advice on what can be changed in the input for the output of the black-box model to change. Counterfactuals are user-friendly and provide actionable advice for achieving the desired output from the AI system. While extensively researched in supervised learning, there are few methods applying them to reinforcement learning (RL). In this work, we explore the reasons for the underrepresentation of a powerful explanation method in RL. We start by reviewing the current work in counterfactual explanations in supervised learning. Additionally, we explore the differences between counterfactual explanations in supervised learning and RL and identify the main challenges that prevent the adoption of methods from supervised in reinforcement learning. Finally, we redefine counterfactuals for RL and propose research directions for implementing counterfactuals in RL.

Jasmina Gajcin, James McCarthy, Rahul Nair et al.

A well-defined reward function is crucial for successful training of an reinforcement learning (RL) agent. However, defining a suitable reward function is a notoriously challenging task, especially in complex, multi-objective environments. Developers often have to resort to starting with an initial, potentially misspecified reward function, and iteratively adjusting its parameters, based on observed learned behavior. In this work, we aim to automate this process by proposing ITERS, an iterative reward shaping approach using human feedback for mitigating the effects of a misspecified reward function. Our approach allows the user to provide trajectory-level feedback on agent's behavior during training, which can be integrated as a reward shaping signal in the following training iteration. We also allow the user to provide explanations of their feedback, which are used to augment the feedback and reduce user effort and feedback frequency. We evaluate ITERS in three environments and show that it can successfully correct misspecified reward functions.

Jasmina Gajcin, Ivana Dusparic

While reinforcement learning (RL) algorithms have been successfully applied to numerous tasks, their reliance on neural networks makes their behavior difficult to understand and trust. Counterfactual explanations are human-friendly explanations that offer users actionable advice on how to alter the model inputs to achieve the desired output from a black-box system. However, current approaches to generating counterfactuals in RL ignore the stochastic and sequential nature of RL tasks and can produce counterfactuals that are difficult to obtain or do not deliver the desired outcome. In this work, we propose RACCER, the first RL-specific approach to generating counterfactual explanations for the behavior of RL agents. We first propose and implement a set of RL-specific counterfactual properties that ensure easily reachable counterfactuals with highly probable desired outcomes. We use a heuristic tree search of the agent's execution trajectories to find the most suitable counterfactuals based on the defined properties. We evaluate RACCER in two tasks as well as conduct a user study to show that RL-specific counterfactuals help users better understand agents' behavior compared to the current state-of-the-art approaches.

Jasmina Gajcin, Ivana Dusparic

Despite notable results in various fields over the recent years, deep reinforcement learning (DRL) algorithms lack transparency, affecting user trust and hindering their deployment to high-risk tasks. Causal confusion refers to a phenomenon where an agent learns spurious correlations between features which might not hold across the entire state space, preventing safe deployment to real tasks where such correlations might be broken. In this work, we examine whether an agent relies on spurious correlations in critical states, and propose an alternative subset of features on which it should base its decisions instead, to make it less susceptible to causal confusion. Our goal is to increase transparency of DRL agents by exposing the influence of learned spurious correlations on its decisions, and offering advice to developers about feature selection in different parts of state space, to avoid causal confusion. We propose ReCCoVER, an algorithm which detects causal confusion in agent's reasoning before deployment, by executing its policy in alternative environments where certain correlations between features do not hold. We demonstrate our approach in taxi and grid world environments, where ReCCoVER detects states in which an agent relies on spurious correlations and offers a set of features that should be considered instead.

Tom He, Jasmina Gajcin, Ivana Dusparic

Reinforcement learning (RL) is used in various robotic applications. RL enables agents to learn tasks autonomously by interacting with the environment. The more critical the tasks are, the higher the demand for the robustness of the RL systems. Causal RL combines RL and causal inference to make RL more robust. Causal RL agents use a causal representation to capture the invariant causal mechanisms that can be transferred from one task to another. Currently, there is limited research in Causal RL, and existing solutions are usually not complete or feasible for real-world applications. In this work, we propose CausalCF, the first complete Causal RL solution incorporating ideas from Causal Curiosity and CoPhy. Causal Curiosity provides an approach for using interventions, and CoPhy is modified to enable the RL agent to perform counterfactuals. Causal Curiosity has been applied to robotic grasping and manipulation tasks in CausalWorld. CausalWorld provides a realistic simulation environment based on the TriFinger robot. We apply CausalCF to complex robotic tasks and show that it improves the RL agent's robustness using CausalWorld.

Javier Carnerero-Cano, Massimiliano Pronesti, Radu Marinescu et al.

Large language models (LLMs) are widely used in knowledge-intensive applications but often generate factually incorrect responses. A promising approach to rectify these flaws is correcting LLMs using feedback. Therefore, in this paper, we introduce FactCorrector, a new post-hoc correction method that adapts across domains without retraining and leverages structured feedback about the factuality of the original response to generate a correction. To support rigorous evaluations of factuality correction methods, we also develop the VELI5 benchmark, a novel dataset containing systematically injected factual errors and ground-truth corrections. Experiments on VELI5 and several popular long-form factuality datasets show that the FactCorrector approach significantly improves factual precision while preserving relevance, outperforming strong baselines. We release our code at https://ibm.biz/factcorrector.

Jasmina Gajcin, Jovan Jeromela, Ivana Dusparic

Reinforcement Learning (RL) is a learning paradigm in which the agent learns from its environment through trial and error. Deep reinforcement learning (DRL) algorithms represent the agent's policies using neural networks, making their decisions difficult to interpret. Explaining the behaviour of DRL agents is necessary to advance user trust, increase engagement, and facilitate integration with real-life tasks. Semifactual explanations aim to explain an outcome by providing "even if" scenarios, such as "even if the car were moving twice as slowly, it would still have to swerve to avoid crashing". Semifactuals help users understand the effects of different factors on the outcome and support the optimisation of resources. While extensively studied in psychology and even utilised in supervised learning, semifactuals have not been used to explain the decisions of RL systems. In this work, we develop a first approach to generating semifactual explanations for RL agents. We start by defining five properties of desirable semifactual explanations in RL and then introducing SGRL-Rewind and SGRL-Advance, the first algorithms for generating semifactual explanations in RL. We evaluate the algorithms in two standard RL environments and find that they generate semifactuals that are easier to reach, represent the agent's policy better, and are more diverse compared to baselines. Lastly, we conduct and analyse a user study to assess the participant's perception of semifactual explanations of the agent's actions.

Hyo Jin Do, Zahra Ashktorab, Jasmina Gajcin et al.

The LLM-as-a-judge paradigm enables flexible, user-defined evaluation, but its effectiveness is often limited by the scarcity of diverse, representative data for refining criteria. We present a tool that integrates synthetic data generation into the LLM-as-a-judge workflow, empowering users to create tailored and challenging test cases with configurable domains, personas, lengths, and desired outcomes, including borderline cases. The tool also supports AI-assisted inline editing of existing test cases. To enhance transparency and interpretability, it reveals the prompts and explanations behind each generation. In a user study (N=24), 83% of participants preferred the tool over manually creating or selecting test cases, as it allowed them to rapidly generate diverse synthetic data without additional workload. The generated synthetic data proved as effective as hand-crafted data for both refining evaluation criteria and aligning with human preferences. These findings highlight synthetic data as a promising alternative, particularly in contexts where efficiency and scalability are critical.

Srishti Yadav, Jasmina Gajcin, Erik Miehling et al.

Understanding how different stakeholders perceive risks in AI systems is essential for their responsible deployment. This paper presents a framework for stakeholder-grounded risk assessment by using LLMs, acting as judges to predict and explain risks. Using the Risk Atlas Nexus and GloVE explanation method, our framework generates stakeholder-specific, interpretable policies that shows how different stakeholders agree or disagree about the same risks. We demonstrate our method using three real-world AI use cases of medical AI, autonomous vehicles, and fraud detection domain. We further propose an interactive visualization that reveals how and why conflicts emerge across stakeholder perspectives, enhancing transparency in conflict reasoning. Our results show that stakeholder perspectives significantly influence risk perception and conflict patterns. Our work emphasizes the importance of these stakeholder-aware explanations needed to make LLM-based evaluations more transparent, interpretable, and aligned with human-centered AI governance goals.

Erik Miehling, Karthikeyan Natesan Ramamurthy, Kush R. Varshney et al.

The endowment of AI with reasoning capabilities and some degree of agency is widely viewed as a path toward more capable and generalizable systems. Our position is that the current development of agentic AI requires a more holistic, systems-theoretic perspective in order to fully understand their capabilities and mitigate any emergent risks. The primary motivation for our position is that AI development is currently overly focused on individual model capabilities, often ignoring broader emergent behavior, leading to a significant underestimation in the true capabilities and associated risks of agentic AI. We describe some fundamental mechanisms by which advanced capabilities can emerge from (comparably simpler) agents simply due to their interaction with the environment and other agents. Informed by an extensive amount of existing literature from various fields, we outline mechanisms for enhanced agent cognition, emergent causal reasoning ability, and metacognitive awareness. We conclude by presenting some key open challenges and guidance for the development of agentic AI. We emphasize that a systems-level perspective is essential for better understanding, and purposefully shaping, agentic AI systems.

Jasmina Gajcin, Ivana Dusparic

Understanding how failure occurs and how it can be prevented in reinforcement learning (RL) is necessary to enable debugging, maintain user trust, and develop personalized policies. Counterfactual reasoning has often been used to assign blame and understand failure by searching for the closest possible world in which the failure is avoided. However, current counterfactual state explanations in RL can only explain an outcome using just the current state features and offer no actionable recourse on how a negative outcome could have been prevented. In this work, we propose ACTER (Actionable Counterfactual Sequences for Explaining Reinforcement Learning Outcomes), an algorithm for generating counterfactual sequences that provides actionable advice on how failure can be avoided. ACTER investigates actions leading to a failure and uses the evolutionary algorithm NSGA-II to generate counterfactual sequences of actions that prevent it with minimal changes and high certainty even in stochastic environments. Additionally, ACTER generates a set of multiple diverse counterfactual sequences that enable users to correct failure in the way that best fits their preferences. We also introduce three diversity metrics that can be used for evaluating the diversity of counterfactual sequences. We evaluate ACTER in two RL environments, with both discrete and continuous actions, and show that it can generate actionable and diverse counterfactual sequences. We conduct a user study to explore how explanations generated by ACTER help users identify and correct failure.

Jasmina Gajcin, Erik Miehling, Rahul Nair et al.

Using LLMs to evaluate text, that is, LLM-as-a-judge, is increasingly being used at scale to augment or even replace human annotations. As such, it is imperative that we understand the potential biases and risks of doing so. In this work, we propose an approach for extracting high-level concept-based global policies from LLM-as-a-Judge. Our approach consists of two algorithms: 1) CLoVE (Contrastive Local Verifiable Explanations), which generates verifiable, concept-based, contrastive local explanations and 2) GloVE (Global Verifiable Explanations), which uses iterative clustering, summarization and verification to condense local rules into a global policy. We evaluate GloVE on seven standard benchmarking datasets for content harm detection. We find that the extracted global policies are highly faithful to decisions of the LLM-as-a-Judge. Additionally, we evaluated the robustness of global policies to text perturbations and adversarial attacks. Finally, we conducted a user study to evaluate user understanding and satisfaction with global policies.

Jasmina Gajcin, Rahul Nair, Tejaswini Pedapati et al.

In complex tasks where the reward function is not straightforward and consists of a set of objectives, multiple reinforcement learning (RL) policies that perform task adequately, but employ different strategies can be trained by adjusting the impact of individual objectives on reward function. Understanding the differences in strategies between policies is necessary to enable users to choose between offered policies, and can help developers understand different behaviors that emerge from various reward functions and training hyperparameters in RL systems. In this work we compare behavior of two policies trained on the same task, but with different preferences in objectives. We propose a method for distinguishing between differences in behavior that stem from different abilities from those that are a consequence of opposing preferences of two RL agents. Furthermore, we use only data on preference-based differences in order to generate contrasting explanations about agents' preferences. Finally, we test and evaluate our approach on an autonomous driving task and compare the behavior of a safety-oriented policy and one that prefers speed.