Searcharxiv⌕ Search

arXiv subjects

Xiaodan Zhu

Publications and source records attributed to Xiaodan Zhu.

At least 19 recordsLinked to original sources
arXiv2026

IDRBench: Understanding the Capability of Large Language Models on Interdisciplinary Research

Innovation is a key driving force of human civilization. As the body of knowledge has grown considerably, bridging knowledge across different disciplines, where significant innovation often emerges, has become increasingly challenging. The recent advancements in machine learning models, particularly Large Language Models (LLMs), have provided effective access to extensive knowledge sources and shown impressive abilities in reasoning, rendering significant opportunities for interdisciplinary discovery. Our research aims to understand the capabilities of state-of-the-art LLMs in integrating knowledge from different fields for interdisciplinary research (IDR). To address this fundamental problem, we introduce IDRBench, a pioneering framework that includes both datasets and evaluation tasks: (1) IDR Paper Identification, (2) IDR Idea Integration, and (3) IDR Idea Recommendation. Our study on ten mainstream LLMs provides a comprehensive analysis of their behavior and establishes benchmarks and baselines for future research. To the best of our knowledge, IDRBench is the first to provide a comprehensive investigation of LLMs' IDR capability.

cs.CL↗
arXiv2026

HSRM: Hidden-State Reward Models for Test-Time Verification

Large language models can often generate plausible mathematical reasoning traces, but reliably identifying the correct solution among multiple candidates remains a key challenge. Existing test-time reasoning pipelines typically rely on text-based verifiers that re-read each generated solution, making verification an expensive component of inference. Prior work has shown, however, that LLMs often encode correctness-related signals in their internal representations, including awareness of when their own answers are likely to be wrong. Building on this observation, we introduce HSRM, a lightweight hidden-state reward model that verifies candidate solutions by directly reading the generator's internal representations rather than re-processing its text. HSRM extracts hidden states from a frozen generator at reasoning-step boundaries and uses a small Transformer encoder to rank candidates. It is trained from self-generated trajectories with outcome labels, requiring neither human-written process supervision nor a large pretrained verifier. Across four mathematical reasoning benchmarks, HSRM matches or outperforms a 55M-parameter text-only energy verifier in 15 of 16 generator--dataset settings while using only about 2M parameters, providing an efficient alternative to text-only verification by reusing representations already computed during generation.

cs.AI↗
arXiv2026

On the Diversity of Analogy Making in Large Language Models

Large Language Models (LLMs) have demonstrated remarkable potential for analogy making, a core cognitive capability that drives novelty and creativity. While prior research has extensively investigated the applications and underlying mechanisms of LLM-based analogy making, its output diversity remains largely unexplored, despite being essential for broadening cross-domain connections and fostering scientific innovation. In this work, we present a comprehensive evaluation of analogy diversity across ten state-of-the-art open- and closed-source LLMs. Our findings highlight a concerning issue of domain homogeneity, a prevalent tendency for LLMs to generate analogies from a narrow set of target domains, limiting both inter-query and intra-model diversity. Furthermore, our analysis reveals a fundamental trade-off in existing LLM diversity-enhancement methods: increasing output diversity often comes at the expense of output quality. Finally, our causal analysis of LLM information flow reveals substantial differences in the model-sensitive regions governing analogy diversity across LLMs, suggesting a potential mechanism for the observed diversity-quality trade-off. To our knowledge, this is among the first studies to systematically investigate output diversity in LLM-based analogy making.

cs.CL↗
arXiv2026

RedDebate: Safer Responses Through Multi-Agent Red Teaming Debates

We introduce RedDebate, a novel multi-agent debate framework that provides the foundation for Large Language Models (LLMs) to identify and mitigate their unsafe behaviours. AI safety approaches often rely on costly human evaluation or isolated single-model assessment, both constrained by scalability and prone to oversight failures. RedDebate employs collaborative argumentation among multiple LLMs across diverse debate scenarios, enabling them to critically evaluate one another's reasoning and systematically uncover unsafe failure modes through fully automated red-teaming. To support this, we propose designing distinct long-term memory modules that preserve safety-relevant insights from debate interactions and leverage them during subsequent inference, facilitating continuous refinement of model behaviour. Empirical evaluation on safety benchmarks across a diverse set of models demonstrates that RedDebate substantially reduces unsafe outputs. While debate alone allows LLMs to refine their behaviour, the addition of memory yields further error reductions. To the best of our knowledge, RedDebate is the first fully automated framework to unify multi-agent debate and red-teaming to progressively enhance LLM safety without human intervention.

cs.CL↗
arXiv2026

What Am I Missing? Question-Answering as Hidden State Probing

Test-time reasoning has become a significant field of study since the introduction of chain-of-thought reasoning in large language models (LLMs). However, the mechanisms of this reasoning process are still under-explored -- from the same input prompt, and even the same partial solution, LLMs can produce varied answers if sampled multiple times. We propose to leverage question-asking as an inference-time intervention that articulates information about the model's hidden state. To achieve that, we present a student-teacher setting where a student asks questions to a teacher. We train a probe on the student's hidden state before and after asking a question and find it is predictive of the trajectory's final correctness, even before generating the teacher's answer. This suggests there is a meaningful signal from the self-diagnosis that occurs during question generation rather than information transfer from the teacher. We then frame question-asking as a sequential decision problem, using this probe as a quality score, and define a gating policy to ask questions that maximize likelihood of correctness. We find that the success of question-asking as an intervention is largely dependent on the model's self-consistency. Our empirical results show a gap between detection and recovery; while our gating policy captures model correctness and uncertainty, interventions are equally likely to harm correct trajectories as they are to recover incorrect ones. This gap between diagnosis and correction has broader implications on language models' capacity for self-refinement under uncertainty.

cs.CL↗
arXiv2026

Chronicle: A Multimodal Foundation Model for Joint Language and Time Series Understanding

Real-world time series come with text: metadata, descriptions, news, reports. Yet time series foundation models process numerical sequences in isolation, and the multimodal text-and-time-series models that attempt to bridge the two all adapt a pretrained language model post hoc, inheriting representations shaped without ever seeing temporal data. These models are also evaluated almost exclusively against other multimodal baselines, not against the strongest unimodal foundation models in either domain, leaving open whether joint training is needed at all. We present Chronicle, a compact 324M-parameter decoder-only transformer trained from scratch on natural language and time series within a single unified architecture. Both modalities share the same transformer blocks, attention mechanism, and residual stream; the bulk of pretraining uses unimodal batches so cross-modal capability emerges purely from shared parameters, with a short alignment stage that interleaves the two. To our knowledge, Chronicle is the first model jointly pretrained on text and time series from scratch, and the first multimodal model evaluated against dedicated foundation models in both domains. It matches Gemma-3-270M-PT on 19 NLU tasks, sets a new bar for frozen-embedding time series classification on 24 UCR/UEA datasets, and produces multimodal forecasts on Time-MMD that beat every supervised fusion baseline, all from a single backbone.

cs.LG↗
arXiv2026

Confidently Deceptive: How Confidence Amplifies the Risk of LLM Deception

Large language models (LLMs) can produce deceptive responses: outputs that mislead users in service of a contextually or experimentally induced goal. Yet it remains unclear how confidently models deceive and whether higher confidence makes deceptive responses more persuasive to end users. In this paper, we study these basic questions in various models and different deception datasets. We provide a comprehensive study measuring confidence through both verbalized self-reports and a range of logit-based estimators. We show that LLMs deliver deceptive responses with substantial verbalized confidence and that human annotators prefer the higher-confidence deceptive response 78% of the time in paired comparisons. Misalignment fine-tuning amplifies the problem. Confidence in deceptive responses rises across all three benchmarks, increasing the resulting potential risk, with effects generalizing beyond the training distribution. Strikingly, models classify their own deceptive outputs as deceptive at high rates (82.7% under misalignment) while still predicting they would produce them - recognition without avoidance. We argue that confident deception is a distinct alignment risk requiring evaluations that jointly measure deception, confidence, and awareness.

cs.CL↗
arXiv2026

CoDial: Interpretable Task-Oriented Dialogue Systems Through Dialogue Flow Alignment

Building Task-Oriented Dialogue (TOD) systems that generalize across different tasks remains a challenging problem. Data-driven approaches often struggle to transfer effectively to unseen tasks. While recent schema-based TOD frameworks improve generalization by decoupling task logic from language understanding, their reliance on neural or generative models often obscures how task schemas influence behaviour and hence impair interpretability. In this work, we introduce a novel framework, CoDial (Code for Dialogue), at the core of which is converting a predefined task schema to a structured heterogeneous graph and then to programmatic LLM guardrailing code, such as NVIDIA's Colang. The pipeline enables efficient and interpretable alignment of dialogue policies during inference. We introduce two paradigms for LLM guardrailing code generation, $\text{CoDial}_{\text{free}}$ and $\text{CoDial}_{\text{structured}}$, and propose a mechanism that integrates human feedback to iteratively improve the generated code. Empirically, CoDial achieves state-of-the-art (SOTA) performance on the widely used benchmark datasets, while providing inherent interpretability in the design. We additionally demonstrate CoDial's iterative improvement via manual and LLM-aided feedback, making it a practical tool for human-guided alignment of LLMs in unseen domains.

cs.CL↗
arXiv2026

Atomistic Modeling of Methane and Carbon Dioxide Structure I Gas Hydrates Under Pressure: Guest Effects and Properties

Gas hydrates are potential candidates in future energy sources while simultaneously providing structures with extensive applications in carbon capture and storage, gas transport, and important separation processes. Prior research in the field considers the dynamics of the water molecule backbone in particular. We investigated the pressure-enthalpy landscape and mechanical stability envelope of sI methane and carbon dioxide hydrates simulated using DFT. We investigated the effect of the revPBE + DFT-D2 and the SCAN + rVV10 and their treatment of the exchange correlation interactions. We examined the zero pressure material properties, finding that revPBE comparatively underbinds the interactions, causing more flexible structures with large equilibrium volumes. Under pressure, the carbon dioxide molecule was found to align itself parallel to the hexagonal faces of the large cage despite the functional used. Additionally, the property differences are caused by the ability of the carbon dioxide molecule to rotate and disperse the changes in the energy landscape in ways that methane molecules cannot. This computational methodology describes the elastic stability of gas hydrate, marginal stability, and critical differences across important molecular interactions, confirming experimentally observed restrictions in guest molecule rotations and novel pressure behaviors under hydrostatic loads

physics.chem-ph↗
arXiv2026

ADAPTive Input Training for Many-to-One Pre-Training on Time-Series Classification

Recent work on time-series models has leveraged self-supervised training to learn meaningful features and patterns in order to improve performance on downstream tasks and generalize to unseen modalities. While these pretraining methods have shown great promise in one-to-many scenarios, where a model is pre-trained on one dataset and fine-tuned on a downstream dataset, they have struggled to generalize to new datasets when more datasets are added during pre-training. This is a fundamental challenge in building foundation models for time-series data, as it limits the ability to develop models that can learn from a large variety of diverse datasets available. To address this challenge, we present a new pre-training paradigm for time-series data called ADAPT, which can efficiently align the physical properties of data in the time-series domain, enabling mixed-batch pre-training despite the extreme discrepancies in the input sizes and channel dimensions of pre-training data. We trained on 162 time-series classification datasets and set new state-of-the-art performance for classification benchmarks. We successfully train a model within the time-series domain on a wide range of datasets simultaneously, which is a major building block for building generalist foundation models in time-series domains.

cs.LG↗
arXiv2026

Jump Start or False Start? A Theoretical and Empirical Evaluation of LLM-initialized Bandits

The recent advancement of Large Language Models (LLMs) offers new opportunities to generate user preference data to warm-start bandits. Recent studies on contextual bandits with LLM initialization (CBLI) have shown that these synthetic priors can significantly lower early regret. However, these findings assume that LLM-generated choices are reasonably aligned with actual user preferences. In this paper, we systematically examine how LLM-generated preferences perform when random and label-flipping noise is injected into the synthetic training data. For aligned domains, we find that warm-starting remains effective up to 30% corruption, loses its advantage around 40%, and degrades performance beyond 50%. When there is systematic misalignment, even without added noise, LLM-generated priors can lead to higher regret than a cold-start bandit. To explain these behaviors, we develop a theoretical analysis that decomposes the effect of random label noise and systematic misalignment on the prior error driving the bandit's regret, and derive a sufficient condition under which LLM-based warm starts are provably better than a cold-start bandit. We validate these results across multiple conjoint datasets and LLMs, showing that estimated alignment reliably tracks when warm-starting improves or degrades recommendation quality.

cs.LG↗
arXiv2026

SPARE: Single-Pass Annotation with Reference-Guided Evaluation for Automatic Process Supervision and Reward Modelling

Process or step-wise supervision has played a crucial role in advancing complex multi-step reasoning capabilities of Large Language Models (LLMs). However, efficient, high-quality automated process annotation remains a significant challenge. To address this, we introduce Single-Pass Annotation with Reference-Guided Evaluation (SPARE), a novel structured framework that enables efficient per-step annotation by jointly aligning solution steps to reference solutions and determine its accuracy with explicit reasoning in single generation. We demonstrate SPARE's effectiveness across four diverse datasets spanning mathematical reasoning (GSM8K, MATH), multi-hop question answering (MuSiQue-Ans), and spatial reasoning (SpaRP), showing consistent improvements in two applications: (1) training Process Reward Models (PRMs) for ranking and aggregating multiple generations, and (2) fine-tuning models via offline reinforcement learning for greedy decoding. On ProcessBench, SPARE demonstrates data-efficient out-of-distribution generalization, using only $\sim$16% of training samples compared to human-labeled and other synthetically trained baselines. Additionally, it achieves competitive performance with MCTS-based methods while offering 2.3$\times$ speedup in terms of total token count. Manual analysis reveals complementary precision-recall characteristics with MCTS approaches, suggesting potential for ensemble methods. These results establish SPARE as a practical and scalable solution for automatic process supervision in LLM reasoning.

cs.CL↗
arXiv2026

Entropy-Gated Branching for Efficient Test-Time Reasoning

Test-time compute methods can significantly improve the reasoning capabilities and problem-solving accuracy of large language models (LLMs). However, these approaches require substantially more computational resources, with most compute wasted on exploring low-diversity branches where the model already exhibits high confidence. We observe that a small subset of uncertain reasoning steps has a disproportionately large impact on final prediction accuracy, and branching at these critical junctures tends to yield more diverse and higher-quality candidate reasoning steps. We propose Entropy-Gated Branching (EGB), which branches only at high-uncertainty steps and prunes expansions with a lightweight verifier. On mathematical and financial reasoning benchmarks, EGB improves accuracy by 22.6% over standard inference while operating 31%-75% faster across math benchmarks than test-time beam search with higher performance. Our results show that dynamic resource allocation during inference can substantially improve both efficiency and effectiveness, offering a more scalable pathway to enhanced LLM reasoning capabilities.

cs.CL↗
arXiv2026

Chat-TS: Enhancing Multi-Modal Reasoning Over Time-Series and Natural Language Data

Large language models are being rapidly deployed across many fields such as healthcare, finance, transportation, and energy, where time-series data are fundamental components. The current works are still limited in their ability to perform reasoning that involves both time-series and the corresponding textual content. We address this gap by introducing Chat-TS, a large language model (LLM) based framework designed to support reasoning over time series and textual data. Unlike traditional models, Chat-TS integrates time-series tokens into LLMs' vocabulary, enhancing its reasoning ability over both modalities without compromising core natural language capabilities. To support learning and evaluation, we contribute new datasets: the TS Instruct Training Dataset (pairing diverse time-series data with relevant text instructions and responses for instruction tuning), the TS Instruct Question and Answer (QA) Gold Dataset (multiple-choice questions to evaluate multimodal reasoning), and a TS Instruct Quantitative Probing Set (a small subset of TS Instruct QA reasoning tasks alongside math and decision-making questions for LLM evaluation). We design a training strategy to preserve the inherent reasoning capabilities of LLMs while augmenting them for time-series reasoning. Experiments show that Chat-TS achieves state-of-the-art performance in multimodal reasoning tasks by maintaining strong natural language proficiency while improving time-series reasoning.

cs.AI↗
arXiv2026

Detect, Explain, Escalate: Sustainable Dialogue Breakdown Management for LLM Agents

Large Language Models (LLMs) have demonstrated substantial capabilities in conversational AI applications, yet their susceptibility to dialogue breakdowns poses significant challenges to deployment reliability and user trust. This paper introduces a "Detect, Explain, Escalate" framework to manage dialogue breakdowns in LLM-powered agents, emphasizing resource-efficient operation. Our approach integrates two key strategies: (1) We fine-tune a compact 8B-parameter model, augmented with teacher-generated reasoning traces, which serves as an efficient real-time breakdown detector and explainer. This model demonstrates robust classification and calibration on English and Japanese dialogues, and generalizes to the BETOLD dataset, improving accuracy by 7% over its baseline. (2) We systematically evaluate frontier LLMs using advanced prompting (few-shot, chain-of-thought, analogical reasoning) for high-fidelity breakdown assessment. These are integrated into an "escalation" architecture where our efficient detector defers to larger models only when necessary, substantially reducing operational costs and computational overhead. Our fine-tuned model and prompting strategies achieve state-of-the-art performance on DBDC5 and strong results on BETOLD, outperforming specialized classifiers on DBDC5 and narrowing the performance gap to larger proprietary models. The proposed monitor-escalate pipeline reduces inference costs by 54%, providing a cost-effective and interpretable solution for robust conversational AI in high-impact domains. Code and models are publicly available.

cs.CL↗
arXiv2025

On the Robustness of Verbal Confidence of LLMs in Adversarial Attacks

Robust verbal confidence generated by large language models (LLMs) is crucial for the deployment of LLMs to help ensure transparency, trust, and safety in many applications, including those involving human-AI interactions. In this paper, we present the first comprehensive study on the robustness of verbal confidence under adversarial attacks. We introduce attack frameworks targeting verbal confidence scores through both perturbation and jailbreak-based methods, and demonstrate that these attacks can significantly impair verbal confidence estimates and lead to frequent answer changes. We examine a variety of prompting strategies, model sizes, and application domains, revealing that current verbal confidence is vulnerable and that commonly used defence techniques are largely ineffective or counterproductive. Our findings underscore the need to design robust mechanisms for confidence expression in LLMs, as even subtle semantic-preserving modifications can lead to misleading confidence in responses.

cs.CL↗
arXiv2025

LLMs as Planning Formalizers: A Survey for Leveraging Large Language Models to Construct Automated Planning Models

Large Language Models (LLMs) excel in various natural language tasks but often struggle with long-horizon planning problems requiring structured reasoning. This limitation has drawn interest in integrating neuro-symbolic approaches within the Automated Planning (AP) and Natural Language Processing (NLP) communities. However, identifying optimal AP deployment frameworks can be daunting and introduces new challenges. This paper aims to provide a timely survey of the current research with an in-depth analysis, positioning LLMs as tools for formalizing and refining planning specifications to support reliable off-the-shelf AP planners. By systematically reviewing the current state of research, we highlight methodologies, and identify critical challenges and future directions, hoping to contribute to the joint research on NLP and Automated Planning.

cs.AI↗
arXiv2025

Towards Low-Resource Alignment to Diverse Perspectives with Sparse Feedback

As language models have a greater impact on society, it is important to ensure they are aligned to a diverse range of perspectives and are able to reflect nuance in human values. However, the most popular training paradigms for modern language models often assume there is one optimal answer for every query, leading to generic responses and poor alignment. In this work, we aim to enhance pluralistic alignment of language models in a low-resource setting with two methods: pluralistic decoding and model steering. We empirically demonstrate that model steering offers consistent improvement over zero-shot and few-shot baselines with only 50 annotated samples. Our proposed methods decrease false positives in several high-stakes tasks such as hate speech detection and misinformation detection, and improves the distributional alignment to human values in GlobalOpinionQA. We hope our work highlights the importance of diversity and how language models can be adapted to consider nuanced perspectives.

cs.CL↗