arXiv subjects

Hao Liao

Publications and source records attributed to Hao Liao.

At least 19 recordsLinked to original sources

arXiv2026

Poisson-Gamma Modeling of Inter-Relational Dependencies in Dynamic Knowledge Graphs

Dynamic knowledge graphs are ubiquitous in today's AI applications, as we represent molecular structures, social relationships, and language information using these graph models. As knowledge graphs evolve over time and are often noisy and incomplete, modeling their temporal and relational dependencies becomes crucial for downstream tasks. To address these challenges, this paper proposes PGRE (Poisson-Gamma Relational Evolution), a probabilistic model for modeling inter-relational dependencies in dynamic knowledge graphs. PGRE represents multi-relational temporal links via a Poisson-Bernoulli formulation. It introduces Gamma-distributed latent variables to capture entity-factor associations and cross-relation dependencies mediated by shared latent communities. A Gamma Markov process further models the temporal evolution of these latent variables, enabling principled characterization of relational dynamics. Experiments on benchmark datasets show that PGRE achieves competitive performance in link prediction, particularly in sparse settings, while revealing meaningful relational evolution patterns in dynamic knowledge graphs.

cs.LG↗

arXiv2026

Text Distance from Nested and Hierarchical Repetitions: A Compression-Based Perspective

We present a new method for structural sequence analysis grounded in Algorithmic Information Theory (AIT). At its core is the Ladderpath approach, which extracts nested and hierarchical relationships among repeated substructures in linguistic sequences -- an instantiation of AIT's principle of describing data through minimal generative programs. These structures are then used to define three distance measures: a normalized compression distance (NCD), and two alternative distances derived directly from the Ladderpath representation. Integrated with a $k$-nearest neighbor classifier, these distances achieve strong and consistent performance across in-distribution, out-of-distribution (OOD), and few-shot text classification tasks. In particular, all three methods outperform both gzip-based NCD and BERT under OOD and low-resource settings. These results demonstrate that the structured representations captured by Ladderpath preserve intrinsic properties of sequences and provide a lightweight, interpretable, and training-free alternative for text modeling. This work highlights the potential of AIT-based approaches for structural and domain-agnostic sequence understanding.

cs.CL↗

arXiv2026

MINDGAMES: A Live Arena for Evaluating Social and Strategic Reasoning in Multi-Agent LLMs

Large language models (LLMs) are increasingly deployed as interactive agents, yet their capacity for social and strategic reasoning over extended interaction remains poorly understood. Existing evaluations rely on static vignettes or single-game benchmarks that cannot capture the sustained, multi-faceted reasoning that real-world multi-agent settings demand. We introduce Mindgames, a multi-game arena and evaluation platform for LLM agents that operationalizes complementary reasoning demands relevant to ``theory of mind'': belief attribution under hidden information, opponent modeling through repeated strategic interaction, cooperative inference under knowledge asymmetries, and sustained deception in social deduction. Built on TextArena, Mindgames provides a unified interaction interface, TrueSkill-based rating, and full trajectory logging across four game environments. We instantiate Mindgames through a 2025 competition cycle hosted at a major AI conference, which assessed 944 submitted agents from 76 teams across four games: Colonel Blotto, Iterated Prisoner's Dilemma, Codenames, and Secret Mafia. Our analysis surfaces both agent-level and evaluation-level limitations: brittle rule adherence remains a major bottleneck, top-performing systems repeatedly rely on explicit structural scaffolding, and leaderboard validity differs sharply across environments. In particular, failure-heavy environments can reward robustness to opponent errors as much as strategic ability, with Secret Mafia exhibiting a pronounced error-survival confound in this cycle. We release a dataset of 29,571 multi-agent games with turn-level observations, actions, and rewards, together with MG-Ref, a deterministic offline tournament protocol that scores new agents against a frozen reference pool of top-ranked, low-error Stage~II submissions under the same error-attribution lens used in this analysis.

cs.AI↗

arXiv2026

PersonaArena: Dynamic Simulation for Evaluating and Enhancing Persona-Level Role-Playing in Large Language Models

Large language models (LLMs) increasingly serve as interactive social agents, yet their ability to maintain coherent and authentic persona-level role-playing remains limited, particularly in realistic social scenarios. Existing research predominantly focuses on character-level settings and relies on static evaluation formats, failing to capture the complexity of everyday social interactions. In this work, we present PersonaArena, a dynamic simulation framework for evaluating and improving persona-level role-playing in LLMs. PersonaArena leverages a large, filtered corpus of user-generated social content to construct a nuanced persona bank, and elicits multi-turn, context-rich interactions within simulated social environments. Our framework features a multi-agent debating judge for holistic and unbiased assessment. Through extensive experiments, we demonstrate that PersonaArena enables rigorous evaluation and enhancement of LLMs' role-playing capabilities, advancing the development of more authentic and socially adept AI agents.

cs.AI↗

arXiv2026

Toward Consistent World Models with Multi-Token Prediction and Latent Semantic Enhancement

Whether Large Language Models (LLMs) develop coherent internal world models remains a core debate. While conventional Next-Token Prediction (NTP) focuses on one-step-ahead supervision, Multi-Token Prediction (MTP) has shown promise in learning more structured representations. In this work, we provide a theoretical perspective analyzing the gradient inductive bias of MTP, supported by empirical evidence, showing that MTP promotes the convergence toward internal belief states by inducing representational contractivity via gradient coupling. However, we reveal that standard MTP often suffers from structural hallucinations, where discrete token supervision encourages illegal shortcuts in latent space that violate environmental constraints. To address this, we propose a novel method Latent Semantic Enhancement MTP (LSE-MTP), which anchors predictions to ground-truth hidden state trajectories. Experiments on synthetic graphs and real-world Manhattan Taxi Ride show that LSE-MTP effectively bridges the gap between discrete tokens and continuous state representations, enhancing representation alignment, reducing structural hallucinations, and improving robustness to perturbations.

cs.LG↗

arXiv2026

Proact-VL: A Proactive VideoLLM for Real-Time AI Companions

Proactive and real-time interactive experiences are essential for human-like AI companions, yet face three key challenges: (1) achieving low-latency inference under continuous streaming inputs, (2) autonomously deciding when to respond, and (3) controlling both quality and quantity of generated content to meet real-time constraints. In this work, we instantiate AI companions through two gaming scenarios, commentator and guide, selected for their suitability for automatic evaluation. We introduce the Live Gaming Benchmark, a large-scale dataset with three representative scenarios: solo commentary, co-commentary, and user guidance, and present Proact-VL, a general framework that shapes multimodal language models into proactive, real-time interactive agents capable of human-like environment perception and interaction. Extensive experiments show Proact-VL achieves superior response latency and quality while maintaining strong video understanding capabilities, demonstrating its practicality for real-time interactive applications.

cs.CV↗

arXiv2025

Interactive AI NPCs Powered by LLMs: Technical Report for the CPDC Challenge 2025

This report presents the solution and results of our team MSRA\_SC in the Commonsense Persona-Grounded Dialogue Challenge (CPDC 2025). We propose a simple yet effective framework that unifies improvements across both GPU Track and API Track. Our method centers on two key components. First, Context Engineering applies dynamic tool pruning and persona clipping for input compression, combined with post-processing techniques such as parameter normalization and function merging. Together with manually refined prompts, this design improves tool call stability, execution reliability, and role-playing guidance. Second, in the GPU Track, we further adopt GRPO training, replacing supervised fine-tuning with reinforcement learning directly optimized by reward signals. This mitigates small-sample overfitting and significantly enhances task-oriented dialogue performance. In the final evaluation, our team ranks 1st in Task 2 API, 2nd in Task 1 API, and 3rd in both Task 3 API and GPU track, demonstrating the effectiveness of our approach. Our code is publicly available at https://gitlab.aicrowd.com/nikoo_yu/cpdc-2025-winning-solution

cs.AI↗

arXiv2025

Universal learning of nonlocal entropy via local correlations in non-equilibrium quantum states

Characterizing the nonlocal nature of quantum states is a central challenge in the practical application of large-scale quantum computation and simulation. Quantum mutual information (QMI), a fundamental nonlocal measure, plays a key role in quantifying entanglement and has become increasingly important in studying nonequilibrium quantum many-body phenomena, such as many-body localization and thermalization. However, experimental measurement of QMI remains extremely difficult, particularly for nonequilibrium states, which are more complex than ground states. In this Letter, we employ a multilayer perceptron (MLP) to establish a universal mapping between the QMI and local correlations only up to second order for nonequilibrium states generated by quenches in a one-dimensional disordered XXZ model. Our approach provides a practical method for experimentally extracting QMI, readily applicable in platforms such as superconducting qubits. Moreover, this work will establishes a general framework for reconstructing other nonlocal observables, including Fisher information and out-of-time-ordered correlators.

quant-ph↗

arXiv2025

Understanding and Enhancing the Planning Capability of Language Models via Multi-Token Prediction

Large Language Models (LLMs) have achieved impressive performance across diverse tasks but continue to struggle with learning transitive relations, a cornerstone for complex planning. To address this issue, we investigate the Multi-Token Prediction (MTP) paradigm and its impact to transitive relation learning. We theoretically analyze the MTP paradigm using a Transformer architecture composed of a shared output head and a transfer layer. Our analysis reveals that the transfer layer gradually learns the multi-step adjacency information, which in turn enables the backbone model to capture unobserved transitive reachability relations beyond those directly present in the training data, albeit with some inevitable noise in adjacency estimation. Building on this foundation, we propose two strategies to enhance the transfer layer and overall learning quality: Next-Token Injection (NTI) and a Transformer-based transfer layer. Our experiments on both synthetic graphs and the Blocksworld planning benchmark validate our theoretical findings and demonstrate that the improvements significantly enhance the model's path-planning capability. These findings deepen our understanding of how Transformers with MTP learn in complex planning tasks, and provide practical strategies to overcome the transitivity bottleneck, paving the way toward structurally aware and general-purpose planning models.

cs.AI↗

arXiv2025

AIR-Bench: Automated Heterogeneous Information Retrieval Benchmark

Evaluation plays a crucial role in the advancement of information retrieval (IR) models. However, current benchmarks, which are based on predefined domains and human-labeled data, face limitations in addressing evaluation needs for emerging domains both cost-effectively and efficiently. To address this challenge, we propose the Automated Heterogeneous Information Retrieval Benchmark (AIR-Bench). AIR-Bench is distinguished by three key features: 1) Automated. The testing data in AIR-Bench is automatically generated by large language models (LLMs) without human intervention. 2) Heterogeneous. The testing data in AIR-Bench is generated with respect to diverse tasks, domains and languages. 3) Dynamic. The domains and languages covered by AIR-Bench are constantly augmented to provide an increasingly comprehensive evaluation benchmark for community developers. We develop a reliable and robust data generation pipeline to automatically create diverse and high-quality evaluation datasets based on real-world corpora. Our findings demonstrate that the generated testing data in AIR-Bench aligns well with human-labeled testing data, making AIR-Bench a dependable benchmark for evaluating IR models. The resources in AIR-Bench are publicly available at https://github.com/AIR-Bench/AIR-Bench.

cs.IR↗

arXiv2025

Robust and digital hyper-polarization protocol of nuclear spins via magic sequential sequence

Hyper-polarization of nuclear spins is crucial for advancing nuclear magnetic resonance (NMR) and quantum information technologies, as nuclear spins typically exhibit extremely low polarization at room temperature due to their small gyro-magnetic ratios. A promising approach to achieving high nuclear spin polarization is transferring the polarization of electron to nuclear spin. The nitrogen-vacancy (NV) center in diamond has emerged as a highly effective medium for this purpose, and various hyper-polarization protocols have been developed. Among these, the pulsed polarization (PulsePol) method has been extensively studied due to its robustness against static energy shifts of the electron spin. In this study, we introduce a sequential polarization protocol and identify a series of magic and digital sequences for hyper-polarizing nuclear spins. Notably, we demonstrate that some of these magic sequences exhibit significantly greater robustness compared to the PulsePol protocol in the presence of finite half $π$ pulse duration of the protocol. This enhanced robustness positions our protocol as a more suitable candidate for hyper-polarizing nuclear spins species with large gyromagnetic ratios and also ensures better compatibility with high-efficiency readout techniques at high magnetic fields. Additionally, the generality of our protocol allows for its direct application to other solid-state quantum systems beyond the NV center.

quant-ph↗

arXiv2025

Eliminating Out-of-Domain Recommendations in LLM-based Recommender Systems: A Unified View

Recommender systems based on Large Language Models (LLMs) are often plagued by hallucinations of out-of-domain (OOD) items. To address this, we propose RecLM, a unified framework that bridges the gap between retrieval and generation by instantiating three grounding paradigms under a single architecture: embedding-based retrieval, constrained generation over rewritten item titles, and discrete item-tokenizer generation. Using the same backbone LLM and prompts, we systematically compare these three views on public benchmarks. RecLM strictly eradicates OOD recommendations (OOD@10 = 0) across all variants, and the constrained generation variants RecLM-cgen and RecLM-token achieve overall state-of-the-art accuracy compared to both strong ID-based and LLM-based baselines. Our unified view provides a systematic basis for comparing three distinct paradigms to reduce item hallucinations, offering a practical framework to facilitate the application of LLMs to recommendation tasks. Source code is at https://github.com/microsoft/RecAI.

cs.IR↗

arXiv2024

Popularity Ratio Maximization: Surpassing Competitors through Influence Propagation

In this paper, we present an algorithmic study on how to surpass competitors in popularity by strategic promotions in social networks. We first propose a novel model, in which we integrate the Preferential Attachment (PA) model for popularity growth with the Independent Cascade (IC) model for influence propagation in social networks called PA-IC model. In PA-IC, a popular item and a novice item grab shares of popularity from the natural popularity growth via the PA model, while the novice item tries to gain extra popularity via influence cascade in a social network. The popularity ratio is defined as the ratio of the popularity measure between the novice item and the popular item. We formulate Popularity Ratio Maximization (PRM) as the problem of selecting seeds in multiple rounds to maximize the popularity ratio in the end. We analyze the popularity ratio and show that it is monotone but not submodular. To provide an effective solution, we devise a surrogate objective function and show that empirically it is very close to the original objective function while theoretically, it is monotone and submodular. We design two efficient algorithms, one for the overlapping influence and non-overlapping seeds (across rounds) setting and the other for the non-overlapping influence and overlapping seed setting, and further discuss how to deal with other models and problem variants. Our empirical evaluation further demonstrates that the proposed PRM-IMM method consistently achieves the best popularity promotion compared to other methods. Our theoretical and empirical analyses shed light on the interplay between influence maximization and preferential attachment in social networks.

cs.SI↗

arXiv2024

Exploring Loss Landscapes through the Lens of Spin Glass Theory

In the past decade, significant strides in deep learning have led to numerous groundbreaking applications. Despite these advancements, the understanding of the high generalizability of deep learning, especially in such an over-parametrized space, remains limited. For instance, in deep neural networks (DNNs), their internal representations, decision-making mechanism, absence of overfitting in an over-parametrized space, superior generalizability, etc., remain less understood. Successful applications are often considered as empirical rather than scientific achievement. This paper delves into the loss landscape of DNNs through the lens of spin glass in statistical physics, a system characterized by a complex energy landscape with numerous metastable states, as a novel perspective in understanding how DNNs work. We investigated the loss landscape of single hidden layer neural networks activated by Rectified Linear Unit (ReLU) function, and introduced several protocols to examine the analogy between DNNs and spin glass. Specifically, we used (1) random walk in the parameter space of DNNs to unravel the structures in their loss landscape; (2) a permutation-interpolation protocol to study the connection between copies of identical regions in the loss landscape due to the permutation symmetry in the hidden layers; (3) hierarchical clustering to reveal the hierarchy among trained solutions of DNNs, reminiscent of the so-called Replica Symmetry Breaking (RSB) phenomenon (i.e. the Parisi solution) in spin glass; (4) finally, we examine the relationship between the ruggedness of DNN's loss landscape and its generalizability, showing an improvement of flattened minima.

cond-mat.dis-nn↗

arXiv2024

Aligning Large Language Models for Controllable Recommendations

Inspired by the exceptional general intelligence of Large Language Models (LLMs), researchers have begun to explore their application in pioneering the next generation of recommender systems - systems that are conversational, explainable, and controllable. However, existing literature primarily concentrates on integrating domain-specific knowledge into LLMs to enhance accuracy, often neglecting the ability to follow instructions. To address this gap, we initially introduce a collection of supervised learning tasks, augmented with labels derived from a conventional recommender model, aimed at explicitly improving LLMs' proficiency in adhering to recommendation-specific instructions. Subsequently, we develop a reinforcement learning-based alignment procedure to further strengthen LLMs' aptitude in responding to users' intentions and mitigating formatting errors. Through extensive experiments on two real-world datasets, our method markedly advances the capability of LLMs to comply with instructions within recommender systems, while sustaining a high level of accuracy performance.

cs.IR↗

arXiv2024

Re-Search for The Truth: Multi-round Retrieval-augmented Large Language Models are Strong Fake News Detectors

The proliferation of fake news has had far-reaching implications on politics, the economy, and society at large. While Fake news detection methods have been employed to mitigate this issue, they primarily depend on two essential elements: the quality and relevance of the evidence, and the effectiveness of the verdict prediction mechanism. Traditional methods, which often source information from static repositories like Wikipedia, are limited by outdated or incomplete data, particularly for emerging or rare claims. Large Language Models (LLMs), known for their remarkable reasoning and generative capabilities, introduce a new frontier for fake news detection. However, like traditional methods, LLM-based solutions also grapple with the limitations of stale and long-tail knowledge. Additionally, retrieval-enhanced LLMs frequently struggle with issues such as low-quality evidence retrieval and context length constraints. To address these challenges, we introduce a novel, retrieval-augmented LLMs framework--the first of its kind to automatically and strategically extract key evidence from web sources for claim verification. Employing a multi-round retrieval strategy, our framework ensures the acquisition of sufficient, relevant evidence, thereby enhancing performance. Comprehensive experiments across three real-world datasets validate the framework's superiority over existing methods. Importantly, our model not only delivers accurate verdicts but also offers human-readable explanations to improve result interpretability.

cs.CL↗

arXiv2024

Loophole-free test of macroscopic realism via high-order correlations of measurement

Test of {macroscopic realism} (MR) is key to understanding the foundation of quantum mechanics. Due to the existence of the {non-invasive measurability} loophole and other interpretation loopholes, however, such test remains an open question. Here we propose a general inequality based on high-order correlations of measurements for a loophole-free test of MR at the weak signal limit. Importantly, the inequality is established using the statistics of \textit{raw data} recorded by classical devices, without requiring a specific model for the measurement process, so its violation would falsify MR without the interpretation loophole. The non-invasive measurability loophole is also closed, since the weak signal limit can be verified solely by measurement data (using the relative scaling behaviors of different orders of correlations). We demonstrate that the inequality can be broken by a quantum spin model. The inequality proposed here provides an unambiguous test of the MR principle and is also useful to characterizing {quantum coherence}.

quant-ph↗

arXiv2023

MUSER: A MUlti-Step Evidence Retrieval Enhancement Framework for Fake News Detection

The ease of spreading false information online enables individuals with malicious intent to manipulate public opinion and destabilize social stability. Recently, fake news detection based on evidence retrieval has gained popularity in an effort to identify fake news reliably and reduce its impact. Evidence retrieval-based methods can improve the reliability of fake news detection by computing the textual consistency between the evidence and the claim in the news. In this paper, we propose a framework for fake news detection based on MUlti-Step Evidence Retrieval enhancement (MUSER), which simulates the steps of human beings in the process of reading news, summarizing, consulting materials, and inferring whether the news is true or fake. Our model can explicitly model dependencies among multiple pieces of evidence, and perform multi-step associations for the evidence required for news verification through multi-step retrieval. In addition, our model is able to automatically collect existing evidence through paragraph retrieval and key evidence selection, which can save the tedious process of manual evidence collection. We conducted extensive experiments on real-world datasets in different languages, and the results demonstrate that our proposed model outperforms state-of-the-art baseline methods for detecting fake news by at least 3% in F1-Macro and 4% in F1-Micro. Furthermore, it provides interpretable evidence for end users.

cs.SI↗