Current large language models (LLMs) often suffer from hallucination issues, i,e, generating content that appears factual but is actually unreliable. A typical hallucination detection pipeline involves response decomposition (i.e., claim extraction), query generation, evidence collection (i.e., search or retrieval), and claim verification. However, existing methods exhibit limitations in the first two stages, such as context loss during claim extraction and low specificity in query generation, resulting in degraded performance across the hallucination detection pipeline. In this work, we introduce JointCQ https://github.com/pku0xff/JointCQ, a joint claim-and-query generation framework designed to construct an effective and efficient claim-query generator. Our framework leverages elaborately designed evaluation criteria to filter synthesized training data, and finetunes a language model for joint claim extraction and query generation, providing reliable and informative inputs for downstream search and verification. Experimental results demonstrate that our method outperforms previous methods on multiple open-domain QA hallucination detection benchmarks, advancing the goal of more trustworthy and transparent language model systems.

Can large language model (LLM) agents reproduce the complex social dynamics that characterize human online behavior -- shaped by homophily, reciprocity, and social validation -- and what memory and learning mechanisms enable such dynamics to emerge? We present a multi-agent LLM simulation framework in which agents repeatedly interact, evaluate one another, and adapt their behavior through in-context learning accelerated by a coaching signal. To model human social behavior, we design behavioral reward functions that capture core drivers of online engagement, including social interaction, information seeking, self-presentation, coordination, and emotional support. These rewards align agent objectives with empirically observed user motivations, enabling the study of how network structures and group formations emerge from individual decision-making. Our experiments show that coached LLM agents develop stable interaction patterns and form emergent social ties, yielding network structures that mirror properties of real online communities. By combining behavioral rewards with in-context adaptation, our framework establishes a principled testbed for investigating collective dynamics in LLM populations and reveals how artificial agents may approximate or diverge from human-like social behavior.

Difficulty-controllable question generation for reading comprehension has gained significant attention in the field of education as a fundamental tool for adaptive learning support. Although several neural question generation methods have recently succeeded in controlling difficulty, conventional approaches still face two major limitations. First, they cannot directly generate multiple-choice questions, which are the most widely used question type in educational contexts. Second, they are not explicitly trained to optimize the accuracy of difficulty control, leaving room for further improvement in difficulty controllability. To address these limitations, this study proposes a novel difficulty-controllable multiple-choice question generation method for reading comprehension which leverages a large language model trained using a direct preference optimization technique to improve the accuracy of difficulty control.

With the goal of improving the security of Internet protocols, we seek faster, semi-automatic methods to discover new vulnerabilities in protocols such as DNS, BGP, and others. To this end, we introduce the LLM-Assisted Protocol Attack Discovery (LAPRAD) methodology, enabling security researchers with some DNS knowledge to efficiently uncover vulnerabilities that would otherwise be hard to detect. LAPRAD follows a three-stage process. In the first, we consult an LLM (GPT-o1) that has been trained on a broad corpus of DNS-related sources and previous DDoS attacks to identify potential exploits. In the second stage, a different LLM automatically constructs the corresponding attack configurations using the ReACT approach implemented via LangChain (DNS zone file generation). Finally, in the third stage, we validate the attack's functionality and effectiveness. Using LAPRAD, we uncovered three new DDoS attacks on the DNS protocol and rediscovered two recently reported ones that were not included in the LLM's training data. The first new attack employs a bait-and-switch technique to trick resolvers into caching large, bogus DNSSEC RRSIGs, reducing their serving capacity to as little as 6%. The second exploits large DNSSEC encryption algorithms (RSA-4096) with multiple keys, thereby bypassing a recently implemented default RRSet limit. The third leverages ANY-type responses to produce a similar effect. These variations of a cache-flushing DDoS attack, called SigCacheFlush, circumvent existing patches, severely degrade resolver query capacity, and impact the latest versions of major DNS resolver implementations.

This study examines the performance of ChatGPT with an experiment in the legal domain. We compare the outcome with it a baseline using regular expressions (Regex), rather than focusing solely on the assessment against human performance. The study reveals that even if ChatGPT has access to the necessary knowledge and competencies, it is unable to assemble them, reason through, in a way that leads to an exhaustive result. This unveils a major limitation of ChatGPT. Intelligence encompasses the ability to break down complex issues and address them according to multiple required competencies, providing a unified and comprehensive solution. In the legal domain, one of the most crucial tasks is reading legal decisions and extracting key passages condensed from principles of law (PoLs), which are then incorporated into subsequent rulings by judges or defense documents by lawyers. In performing this task, artificial intelligence lacks an all-encompassing understanding and reasoning, which makes it inherently limited. Genuine intelligence, remains a uniquely human trait, at least in this particular field.

Time series foundation models (TSFMs) are a class of potentially powerful, general-purpose tools for time series forecasting and related temporal tasks, but their behavior is strongly shaped by subtle inductive biases in their design. Rather than developing a new model and claiming that it is better than existing TSFMs, e.g., by winning on existing well-established benchmarks, our objective is to understand how the various ``knobs'' of the training process affect model quality. Using a mix of theory and controlled empirical evaluation, we identify several design choices (patch size, embedding choice, training objective, etc.) and show how they lead to implicit biases in fundamental model properties (temporal behavior, geometric structure, how aggressively or not the model regresses to the mean, etc.); and we show how these biases can be intuitive or very counterintuitive, depending on properties of the model and data. We also illustrate in a case study on outlier handling how multiple biases can interact in complex ways; and we discuss implications of our results for learning the bitter lesson and building TSFMs.

The proliferation of Large Language Models (LLMs) has created a diverse ecosystem of models with highly varying performance and costs, necessitating effective query routing to balance performance and expense. Current routing systems often rely on a centralized external router trained on a fixed set of LLMs, making them inflexible and prone to poor performance since the small router can not fully understand the knowledge boundaries of different LLMs. We introduce DiSRouter (Distributed Self-Router), a novel paradigm that shifts from centralized control to distributed routing. In DiSRouter, a query traverses a network of LLM agents, each independently deciding whether to answer or route to other agents based on its own self-awareness, its ability to judge its competence. This distributed design offers superior flexibility, scalability, and generalizability. To enable this, we propose a two-stage Self-Awareness Training pipeline that enhances each LLM's self-awareness. Extensive experiments demonstrate that DiSRouter significantly outperforms existing routing methods in utility across various scenarios, effectively distinguishes between easy and hard queries, and shows strong generalization to out-of-domain tasks. Our work validates that leveraging an LLM's intrinsic self-awareness is more effective than external assessment, paving the way for more modular and efficient multi-agent systems.

Evaluating conversational AI systems that use external tools is challenging, as errors can arise from complex interactions among user, agent, and tools. While existing evaluation methods assess either user satisfaction or agents' tool-calling capabilities, they fail to capture critical errors in multi-turn tool-augmented dialogues-such as when agents misinterpret tool results yet appear satisfactory to users. We introduce TRACE, a benchmark of systematically synthesized tool-augmented conversations covering diverse error cases, and SCOPE, an evaluation framework that automatically discovers diverse error patterns and evaluation rubrics in tool-augmented dialogues. Experiments show SCOPE significantly outperforms the baseline, particularly on challenging cases where user satisfaction signals are misleading.

While multi-modal large language models (MLLMs) have made significant progress in recent years, the issue of hallucinations remains a major challenge. To mitigate this phenomenon, existing solutions either introduce additional data for further training or incorporate external or internal information during inference. However, these approaches inevitably introduce extra computational costs. In this paper, we observe that hallucinations in MLLMs are strongly associated with insufficient attention allocated to visual tokens. In particular, the presence of redundant visual tokens disperses the model's attention, preventing it from focusing on the most informative ones. As a result, critical visual cues are often under-attended, which in turn exacerbates the occurrence of hallucinations. Building on this observation, we propose \textbf{PruneHal}, a training-free, simple yet effective method that leverages adaptive KV cache pruning to enhance the model's focus on critical visual information, thereby mitigating hallucinations. To the best of our knowledge, we are the first to apply token pruning for hallucination mitigation in MLLMs. Notably, our method don't require additional training and incurs nearly no extra inference cost. Moreover, PruneHal is model-agnostic and can be seamlessly integrated with different decoding strategies, including those specifically designed for hallucination mitigation. We evaluate PruneHal on several widely used hallucination evaluation benchmarks using four mainstream MLLMs, achieving robust and outstanding results that highlight the effectiveness and superiority of our method. Our code will be publicly available.

This paper presents a question answering system that operates exclusively on a knowledge graph retrieval without relying on retrieval augmented generation (RAG) with large language models (LLMs). Instead, a small paraphraser model is used to paraphrase the entity relationship edges retrieved from querying the knowledge graph. The proposed pipeline is divided into two main stages. The first stage involves pre-processing a document to generate sets of question-answer (QA) pairs. The second stage converts these QAs into a knowledge graph from which graph-based retrieval is performed using embeddings and fuzzy techniques. The graph is queried, re-ranked, and paraphrased to generate a final answer. This work includes an evaluation using LLM-as-a-judge on the CRAG benchmark, which resulted in accuracies of 71.9% and 54.4% using LLAMA-3.2 and GPT-3.5-Turbo,