CRAFT: Forgetting-Aware Intervention-Based Adaptation for Continual Learning

Large language models (LLMs) can acquire new capabilities through fine-tuning, but continual adaptation often leads to catastrophic forgetting. We propose CRAFT, a continual learning framework that avoids updating model weights by instead learning low-rank interventions on hidden representations. CRAFT proceeds in three stages: it first routes each task to a group of similar tasks based on output-distribution divergence; it then fine-tunes the model using a Kullback-Leibler (KL) divergence against the group's prior state, which directly controls forgetting and determines convergence; finally, it merges interventions for the updated task into the shared representation using the same KL signal. This design unifies routing, regularization, and merging through a single KL-based objective. CRAFT improves overall performance and reduces forgetting compared to strong LoRA-based approaches across multiple benchmarks and model scales, while remaining robust to task ordering. These results suggest that controlling adaptation in representation space, guided by output-space divergence, provides a scalable and principled approach to continual learning in LLMs.

Synthetic Users, Real Differences: an Evaluation Framework for User Simulation in Multi-Turn Conversations

There is growing interest in exploring user simulation as an alternative to gathering and scoring real user-chatbot interactions for AI chatbot evaluation. For this purpose, it is important to ensure the realism of the simulation, i.e., the extent to which simulated dialogues reflect real dialogues users have with chatbots. Most existing methods evaluating simulation realism produce coarse quality signal and remain solely at the level of individual dialogues. To support more rigorous evaluation in this area, we propose realsim, an evaluation framework that enables practitioners to take a distributional view of real vs. simulated dialogues along 8 dimensions, covering attributes related to the communicative functions of the interaction, user states, and the surface form of user messages. We then instantiate the framework with a curated dataset of 1K multi-turn task-focused real user-chatbot dialogues that cover 16 domains of chatbot applications. Overall, we find that simulated users tend to struggle at capturing communication frictions that real users introduce to interactions, which could make evaluations based on such simulations overly optimistic. We also observe variability in performance across different domains, which may indicate a need for domain-specific user simulators.

iAgentBench: Benchmarking Sensemaking Capabilities of Information-Seeking Agents on High-Traffic Topics

With the emergence of search-enabled generative QA systems, users are increasingly turning to tools that browse, aggregate, and reconcile evidence across multiple sources on their behalf. Yet many widely used QA benchmarks remain answerable by retrieving a single relevant passage, making them poorly suited for measuring cross-source sensemaking, such as integrating evidence, tracking causal links, and resolving dependencies across facets of a topic. We present iAgentBench, a dynamic ODQA benchmark that targets these higher-level information needs while keeping questions natural and grounded in realistic information-seeking behavior. iAgentBench draws seed topics from real-world attention signals and uses common user intent patterns to construct user-like questions whose answers require combining evidence from multiple sources, not just extracting a single snippet. Each instance is released with traceable evidence and auditable intermediate artifacts that support contamination checks and enable fine-grained diagnosis of failures in retrieval versus synthesis. Experiments across multiple LLMs show that retrieval improves accuracy, but retrieval alone does not reliably resolve these questions, underscoring the need to evaluate evidence use, not just evidence access.

I Think, Therefore I Am Under-Qualified? A Benchmark for Evaluating Linguistic Shibboleth Detection in LLM Hiring Evaluations

This paper introduces a comprehensive benchmark for evaluating how Large Language Models (LLMs) respond to linguistic shibboleths: subtle linguistic markers that can inadvertently reveal demographic attributes such as gender, social class, or regional background. Through carefully constructed interview simulations using 100 validated question-response pairs, we demonstrate how LLMs systematically penalize certain linguistic patterns, particularly hedging language, despite equivalent content quality. Our benchmark generates controlled linguistic variations that isolate specific phenomena while maintaining semantic equivalence, which enables the precise measurement of demographic bias in automated evaluation systems. We validate our approach along multiple linguistic dimensions, showing that hedged responses receive 25.6% lower ratings on average, and demonstrate the benchmark's effectiveness in identifying model-specific biases. This work establishes a foundational framework for detecting and measuring linguistic discrimination in AI systems, with broad applications to fairness in automated decision-making contexts.

RealWebAssist: A Benchmark for Long-Horizon Web Assistance with Real-World Users

To achieve successful assistance with long-horizon web-based tasks, AI agents must be able to sequentially follow real-world user instructions over a long period. Unlike existing web-based agent benchmarks, sequential instruction following in the real world poses significant challenges beyond performing a single, clearly defined task. For instance, real-world human instructions can be ambiguous, require different levels of AI assistance, and may evolve over time, reflecting changes in the user's mental state. To address this gap, we introduce RealWebAssist, a novel benchmark designed to evaluate sequential instruction-following in realistic scenarios involving long-horizon interactions with the web, visual GUI grounding, and understanding ambiguous real-world user instructions. RealWebAssist includes a dataset of sequential instructions collected from real-world human users. Each user instructs a web-based assistant to perform a series of tasks on multiple websites. A successful agent must reason about the true intent behind each instruction, keep track of the mental state of the user, understand user-specific routines, and ground the intended tasks to actions on the correct GUI elements. Our experimental results show that state-of-the-art models struggle to understand and ground user instructions, posing critical challenges in following real-world user instructions for long-horizon web assistance.

Federated Multimodal Learning with Dual Adapters and Selective Pruning for Communication and Computational Efficiency

Federated Learning (FL) enables collaborative learning across distributed clients while preserving data privacy. However, FL faces significant challenges when dealing with heterogeneous data distributions, which can lead to suboptimal global models that fail to generalize across diverse clients. In this work, we propose a novel framework designed to tackle these challenges by introducing a dual-adapter approach. The method utilizes a larger local adapter for client-specific personalization and a smaller global adapter to facilitate efficient knowledge sharing across clients. Additionally, we incorporate a pruning mechanism to reduce communication overhead by selectively removing less impactful parameters from the local adapter. Through extensive experiments on a range of vision and language tasks, our method demonstrates superior performance compared to existing approaches. It achieves higher test accuracy, lower performance variance among clients, and improved worst-case performance, all while significantly reducing communication and computation costs. Overall, the proposed method addresses the critical trade-off between model personalization and generalization, offering a scalable solution for real-world FL applications.

The Order Effect: Investigating Prompt Sensitivity in Closed-Source LLMs

As large language models (LLMs) become integral to diverse applications, ensuring their reliability under varying input conditions is crucial. One key issue affecting this reliability is order sensitivity, wherein slight variations in input arrangement can lead to inconsistent or biased outputs. Although recent advances have reduced this sensitivity, the problem remains unresolved. This paper investigates the extent of order sensitivity in closed-source LLMs by conducting experiments across multiple tasks, including paraphrasing, relevance judgment, and multiple-choice questions. Our results show that input order significantly affects performance across tasks, with shuffled inputs leading to measurable declines in output accuracy. Few-shot prompting demonstrates mixed effectiveness and offers partial mitigation, however, fails to fully resolve the problem. These findings highlight persistent risks, particularly in high-stakes applications, and point to the need for more robust LLMs or improved input-handling techniques in future development.

How Well Do LLMs Represent Values Across Cultures? Empirical Analysis of LLM Responses Based on Hofstede Cultural Dimensions

Large Language Models (LLMs) attempt to imitate human behavior by responding to humans in a way that pleases them, including by adhering to their values. However, humans come from diverse cultures with different values. It is critical to understand whether LLMs showcase different values to the user based on the stereotypical values of a user's known country. We prompt different LLMs with a series of advice requests based on 5 Hofstede Cultural Dimensions -- a quantifiable way of representing the values of a country. Throughout each prompt, we incorporate personas representing 36 different countries and, separately, languages predominantly tied to each country to analyze the consistency in the LLMs' cultural understanding. Through our analysis of the responses, we found that LLMs can differentiate between one side of a value and another, as well as understand that countries have differing values, but will not always uphold the values when giving advice, and fail to understand the need to answer differently based on different cultural values. Rooted in these findings, we present recommendations for training value-aligned and culturally sensitive LLMs. More importantly, the methodology and the framework developed here can help further understand and mitigate culture and language alignment issues with LLMs.

ClaimVer: Explainable Claim-Level Verification and Evidence Attribution of Text Through Knowledge Graphs

In the midst of widespread misinformation and disinformation through social media and the proliferation of AI-generated texts, it has become increasingly difficult for people to validate and trust information they encounter. Many fact-checking approaches and tools have been developed, but they often lack appropriate explainability or granularity to be useful in various contexts. A text validation method that is easy to use, accessible, and can perform fine-grained evidence attribution has become crucial. More importantly, building user trust in such a method requires presenting the rationale behind each prediction, as research shows this significantly influences people's belief in automated systems. It is also paramount to localize and bring users' attention to the specific problematic content, instead of providing simple blanket labels. In this paper, we present $\textit{ClaimVer, a human-centric framework}$ tailored to meet users' informational and verification needs by generating rich annotations and thereby reducing cognitive load. Designed to deliver comprehensive evaluations of texts, it highlights each claim, verifies it against a trusted knowledge graph (KG), presents the evidence, and provides succinct, clear explanations for each claim prediction. Finally, our framework introduces an attribution score, enhancing applicability across a wide range of downstream tasks.

Developing a Framework for Auditing Large Language Models Using Human-in-the-Loop

As LLMs become more pervasive across various users and scenarios, identifying potential issues when using these models becomes essential. Examples include bias, inconsistencies, and hallucination. Although auditing the LLM for these problems is desirable, it is far from being easy or solved. An effective method is to probe the LLM using different versions of the same question. This could expose inconsistencies in its knowledge or operation, indicating potential for bias or hallucination. However, to operationalize this auditing method at scale, we need an approach to create those probes reliably and automatically. In this paper we propose an automatic and scalable solution, where one uses a different LLM along with human-in-the-loop. This approach offers verifiability and transparency, while avoiding circular reliance on the same LLMs, and increasing scientific rigor and generalizability. Specifically, we present a novel methodology with two phases of verification using humans: standardized evaluation criteria to verify responses, and a structured prompt template to generate desired probes. Experiments on a set of questions from TruthfulQA dataset show that we can generate a reliable set of probes from one LLM that can be used to audit inconsistencies in a different LLM. The criteria for generating and applying auditing probes is generalizable to various LLMs regardless of the underlying structure or training mechanism.