Searcharxiv⌕ Search

arXiv subjects

Zihao Fu

Publications and source records attributed to Zihao Fu.

At least 19 recordsLinked to original sources

Beyond Attribute-Centric Fairness: Modelling and Mitigating Unified Bias Representation in Omni-modal Large Language Models

Omni-modal large language models (OLLMs) provide joint multimodal understanding and generation capabilities, making them well-suited to complex environments and promising backbones for next-generation AI. Despite these advances, the harmful stereotypes encoded in such models manifest in increasingly diverse forms, leading to broader and more severe societal consequences. Existing debiasing methods typically impose separate fairness objectives for each sensitive attribute and modality to minimise demographic-dependent variations. However, in omni-modal settings, this attribute-centric paradigm struggles to jointly address diverse social biases with distinct fairness objectives and to generalise beyond predefined attributes. To this end, we propose OmniDebias, one of the first methods for promoting fairness in OLLMs, which employs a bias-centric formulation to extract and mitigate a shared bias representation across attributes and modalities while preserving attribute-related knowledge. Specifically, we exploit activation inconsistencies of a given attribute (e.g., gender) across semantic contexts (e.g., occupations) to disentangle bias from legitimate knowledge. We further consolidate multiple extracted biases into a shared representation, formulating a unified objective that captures the underlying structure across social biases and generalises to unseen attributes. Extensive experiments demonstrate that eliminating unified bias with both post-hoc editing and fine-tuning can consistently improve fairness across diverse attributes and modalities in OLLMs while maintaining favourable utility.

cs.LG↗

FlatSeek: LLM-Driven Symbolic Discovery of Flat Outputs via Backward Data Generation

Differential flatness enables efficient planning and control, but discovering explicit flat outputs for general nonlinear systems remains difficult due to the lack of general methods and supervised data. We propose FlatSeek, a framework combining backward data generation with task-specific large language model (LLM) training. By reversing the defining reconstruction of flatness, we generate system-flat-output pairs with known certificates, then fine-tune an LLM to propose symbolic flat-output candidates for unseen dynamics. On literature and synthetic benchmarks, FlatSeek outperforms both the traditional symbolic methods and the untuned reference models in flat-output discovery success, and uncovers alternative symbolic flat outputs not reported in the literature.

eess.SY↗

SLyM: LLM-Driven Symbolic Lyapunov Function Discovery via Structure Proposal and Coefficient Optimization

Lyapunov functions are the cornerstone of stability analysis for dynamical systems, yet synthesizing a symbolic form remains difficult as no universal constructive algorithm exists. To address this challenge, we introduce SLyM, a framework that harnesses the knowledge and reasoning of large language models (LLMs) to discover symbolic Lyapunov functions. To avoid charging the LLM with ill-suited numerical generation, SLyM decomposes the construction into structure proposal and coefficient optimization: the LLM draws on its prior knowledge of Lyapunov constructions to propose the function structure, whose coefficients then follow from a convex program. Local-search structures are folded back into supervision, extending coverage to systems missed by the initial proposer. Across all benchmarks, SLyM consistently outperforms the evaluated neural, sum-of-squares, and generative baselines.

eess.SY↗

Settle: Learning When to Stop Reasoning

Reasoning models often continue generating after their answers have settled. Settle learns when to stop from answer stability in completed traces. It trains the existing end-of-reasoning token while keeping other predictions close to the base model, and requires only ordinary decoding at inference. On MATH-500 with Qwen3-4B, Settle reduces token count by 40% with a 0.5-percentage-point decrease in accuracy. It gains 6.16 percentage points over supervised fine-tuning on the same traces shortened at their first stable answer, at nearly identical token counts. Its stopping score predicts whether a correct answer will remain correct. Settle extends the accuracy-token-count Pareto frontier of the evaluated stopping methods.

cs.CL↗

Running the Gauntlet: Hard Agentic Tasks

As agentic systems continue to evolve and are widely deployed in real-world scenarios, there is a growing demand to faithfully evaluate their capabilities. However, current benchmarks are typically built on popular applications with relatively simple tasks and focus on a narrow set of capabilities while overlooking broader dimensions, resulting in saturated performance on modern agents and failing to probe their limitations. To this end, we introduce GauntletBench, a web-based benchmark for evaluating agent generalisation in challenging scenarios, focusing on three underexplored capabilities (temporal perception, graphical understanding, and 3D reasoning), across five less-covered professional applications (Video Editor, Workflow Builder, 3D Modeller, Flight Analyser, and Circuit Designer), each with 27 vision-intensive tasks (135 in total). Our benchmark provides a modular pipeline that comprises an environment compatible with both open- and closed-source agent frameworks, a controlled web-based application, a well-structured task suite, and an automated evaluation engine with diverse metrics. Contrary to widespread expectations, our empirical results reveal that frontier agentic systems remain far from achieving human-level performance. Even the state-of-the-art agent achieves only a 28.2% success rate on our GauntletBench, highlighting the limitations in these overlooked capabilities and generalisation. By comparison, non-expert human annotators achieve over 80% success on our challenging yet feasible tasks, revealing the substantial gap between current agent capabilities and those required for complex real-world scenarios.

cs.LG↗

Evaluation of optimisation and Bayesian inference methods for reaction rates in atmospheric chemical mechanisms

Constraining reaction rate coefficients is a central challenge in the development of explicit atmospheric chemical mechanisms, particularly for autoxidation systems where many reaction pathways are only indirectly observed through high-resolution mass spectrometry. In this study, we evaluate rate-coefficient optimisation methods for a toy-case autoxidation mechanism using synthetic data with known ground truth. Two complementary approaches are compared: ODE-constrained neural-network optimisation, which provides efficient point estimates of uncertain rate coefficients, and the Markov Chain Monte Carlo (MCMC) approach, which samples the posterior distribution of rate coefficients and quantifies parameter uncertainty. The methods are tested using direct concentration observations and mass-spectral observations under different noise levels. For unperturbed and low-noise synthetic observations, both methods converged towards the known rate coefficients, with the neural-network optimiser providing faster point estimates. Under high-noise conditions (with the signal-to-noise ratio approximately S / N = 1), however, MCMC was substantially more robust in recovering the rate coefficients. The posterior analysis shows that mass-spectral aggregation broadens credible intervals even at low noise, and that high-noise mass spectra can leave many individual reaction rates weakly identifiable. Posterior predictive validation nevertheless shows how broad parameter uncertainty constrained by MCMC remains consistent with accurate reproduction of the observable mass spectrum. These results demonstrate that point-estimation and Bayesian sampling methods provide complementary information: neural-network optimisation is effective for informative data, whereas MCMC is essential for diagnosing uncertainty, non-uniqueness, and identifiability in noisy or aggregated inverse problems.

stat.ML↗

The Heterogeneous Safety Impacts of Benign Multilingual Fine-Tuning

Fine-tuning a large language model is a ubiquitous method for enhancing its capability on a specific downstream task. However, prior work has shown that this increase in capability comes with a cost: it can increase a model's tendency to respond to unsafe adversarial prompts, even when fine-tuning with non-adversarial data. We present the first comprehensive empirical study of this phenomenon in multilingual settings by fine-tuning Llama-3.2, Qwen3, and Gemma-3 models using benign data translated across nine languages. We find that safety outcomes are highly sensitive to both the choice of fine-tuning language and the evaluation language, with adversarial compliance rates increasing four-fold in some settings. Multilingual safety drift is decoupled from general capability metrics, and occurs heterogeneously across languages and models. Fine-tuning in non-English languages often induces smaller internal representational drifts than English, but these shifts lead models to default to either exaggerated compliance or refusal. As such, assessing fine-tuning impacts solely in English provides inadequate assurance for deployment. To facilitate further research into these cross-lingual safety blind spots, we release the Multilingual-Benign-Tune dataset and the SORRY-Bench-Multilingual evaluation suite.

cs.CL↗

Grounding Text Embeddings in Stakeholder Associations

Text embeddings are widely used to analyse large corpora of complex texts. However, it is unclear whether the embeddings capture the same semantic distances as the human experts using them. Ensuring alignment between embedding representations and human intentions is essential for valid analyses. We present the Stakeholder Grounding Exercise, a method for making expert associations explicit and grounding embedding model results in human understanding. In our primary case study on Danish policy issues, we find that neural text embeddings are substantially less reliable than human experts (19-26 pp gap), and that this misalignment propagates to downstream clustering performance (Spearman $ρ=0.9$ between exercise ranking and cluster quality). A secondary study on US Federal AI use cases replicates the gap (16pp) in English, using a digital protocol and a different community of experts -- demonstrating that the gap is not an artefact of a single instrument or domain. The Stakeholder Grounding Exercise offers a practical method for assessing whether embedding models capture the semantic distinctions that matter most to domain experts.

cs.CL↗

Flexi-LoRA with Input-Adaptive Ranks: Efficient Finetuning for Speech and Reasoning Tasks

Parameter-efficient fine-tuning methods like Low-Rank Adaptation (LoRA) have become essential for deploying large language models, yet their static parameter allocation remains suboptimal for inputs of varying complexity. We present Flexi-LoRA, a novel framework that dynamically adjusts LoRA ranks based on input complexity during both training and inference. Through empirical analysis across question answering, mathematical reasoning, and speech tasks, we demonstrate that maintaining consistency between training and inference dynamics is important for effective adaptation, particularly for sequential reasoning tasks. Our findings reveal that input-dependent parameter allocation achieves higher performance with fewer parameters by optimally matching rank configurations to question complexity. Furthermore, task-specific dependency on rank dynamics varies, with mathematical reasoning tasks exhibiting higher dependency than QA tasks. Successful adaptation manifests not only in correctness but also in reasoning quality and instruction adherence. Flexi-LoRA consistently outperforms static LoRA while using fewer parameters, with performance gains more pronounced on tasks requiring strict reasoning chains. Our approach realizes key benefits of mixture-of-experts frameworks through a more streamlined implementation, reducing parameter redundancy while improving model capabilities. We provide comprehensive empirical studies across diverse tasks, establishing a basis for future work in input-adaptive and efficient fine-tuning approaches.

cs.LG↗

OxEnsemble: Fair Ensembles for Low-Data Classification

We address the problem of fair classification in settings where data is scarce and unbalanced across demographic groups. Such low-data regimes are common in domains like medical imaging, where false negatives can have fatal consequences. We propose a novel approach \emph{OxEnsemble} for efficiently training ensembles and enforcing fairness in these low-data regimes. Unlike other approaches, we aggregate predictions across ensemble members, each trained to satisfy fairness constraints. By construction, \emph{OxEnsemble} is both data-efficient -- carefully reusing held-out data to enforce fairness reliably -- and compute-efficient, requiring little more compute than used to fine-tune or evaluate an existing model. We validate this approach with new theoretical guarantees. Experimentally, our approach yields more consistent outcomes and stronger fairness-accuracy trade-offs than existing methods across multiple challenging medical imaging classification datasets.

cs.CV↗

Evaluating the Ability of Explanations to Disambiguate Models in a Rashomon Set

Explainable artificial intelligence (XAI) is concerned with producing explanations indicating the inner workings of models. For a Rashomon set of similarly performing models, explanations provide a way of disambiguating the behavior of individual models, helping select models for deployment. However explanations themselves can vary depending on the explainer used, and need to be evaluated. In the paper "Evaluating Model Explanations without Ground Truth", we proposed three principles of explanation evaluation and a new method "AXE" to evaluate the quality of feature-importance explanations. We go on to illustrate how evaluation metrics that rely on comparing model explanations against ideal ground truth explanations obscure behavioral differences within a Rashomon set. Explanation evaluation aligned with our proposed principles would highlight these differences instead, helping select models from the Rashomon set. The selection of alternate models from the Rashomon set can maintain identical predictions but mislead explainers into generating false explanations, and mislead evaluation methods into considering the false explanations to be of high quality. AXE, our proposed explanation evaluation method, can detect this adversarial fairwashing of explanations with a 100% success rate. Unlike prior explanation evaluation strategies such as those based on model sensitivity or ground truth comparison, AXE can determine when protected attributes are used to make predictions.

cs.AI↗

SCALPEL: Selective Capability Ablation via Low-rank Parameter Editing for Large Language Model Interpretability Analysis

Large language models excel across diverse domains, yet their deployment in healthcare, legal systems, and autonomous decision-making remains limited by incomplete understanding of their internal mechanisms. As these models integrate into high-stakes systems, understanding how they encode capabilities has become fundamental to interpretability research. Traditional approaches identify important modules through gradient attribution or activation analysis, assuming specific capabilities map to specific components. However, this oversimplifies neural computation: modules may contribute to multiple capabilities simultaneously, while single capabilities may distribute across multiple modules. These coarse-grained analyses fail to capture fine-grained, distributed capability encoding. We present SCALPEL (Selective Capability Ablation via Low-rank Parameter Editing for Large language models), a framework representing capabilities as low-rank parameter subspaces rather than discrete modules. Our key insight is that capabilities can be characterized by low-rank modifications distributed across layers and modules, enabling precise capability removal without affecting others. By training LoRA adapters to reduce distinguishing correct from incorrect answers while preserving general language modeling quality, SCALPEL identifies low-rank representations responsible for particular capabilities while remaining disentangled from others. Experiments across diverse capability and linguistic tasks from BLiMP demonstrate that SCALPEL successfully removes target capabilities while preserving general capabilities, providing fine-grained insights into capability distribution across parameter space. Results reveal that capabilities exhibit low-rank structure and can be selectively ablated through targeted parameter-space interventions, offering nuanced understanding of capability encoding in LLMs.

cs.LG↗

Ripple-assisted adsorption of noble gases on graphene at room temperature

Controllable gas adsorption is critical for both scientific and industrial fields, and high-capacity adsorption of gases on solid surfaces provides a significant promise due to its high-safety and low-energy consumption. However, the adsorption of nonpolar gases, particularly noble gases, poses a considerable challenge under atmospheric pressure and room temperature (RT). Here, we theoretically simulate and experimentally realize the stable adsorption of noble gases like xenon (Xe), krypton (Kr), argon (Ar), and helium (He) on highly rippled graphene at RT. The elemental characteristics of adsorbed Xe are confirmed by electron energy loss spectroscopy and X-ray photoelectron spectroscopy. The adsorbed gas atoms are crystalized with periodic arrangements. These adsorbed noble gases on graphene exhibit high stability at RT and can be completely desorbed at approximately 350 °C without damaging the intrinsic lattice of graphene. The structural and physical properties of graphene are significantly influenced by the adsorbed gas, and they fully recover after desorption. Additionally, this controllable adsorption could be generalized to other layered adsorbents such as NbSe2, MoS2 and carbon nanotubes. We anticipate that this ripple-assisted adsorption will not only re-define the theoretical framework of gas adsorption, but also accelerate advancements in gas storage and separation technologies, as well as enhance the applications in catalysis, surface modification, and other related fields.

cond-mat.mtrl-sci↗

FairImagen: Post-Processing for Bias Mitigation in Text-to-Image Models

Text-to-image diffusion models, such as Stable Diffusion, have demonstrated remarkable capabilities in generating high-quality and diverse images from natural language prompts. However, recent studies reveal that these models often replicate and amplify societal biases, particularly along demographic attributes like gender and race. In this paper, we introduce FairImagen (https://github.com/fuzihaofzh/FairImagen), a post-hoc debiasing framework that operates on prompt embeddings to mitigate such biases without retraining or modifying the underlying diffusion model. Our method integrates Fair Principal Component Analysis to project CLIP-based input embeddings into a subspace that minimizes group-specific information while preserving semantic content. We further enhance debiasing effectiveness through empirical noise injection and propose a unified cross-demographic projection method that enables simultaneous debiasing across multiple demographic attributes. Extensive experiments across gender, race, and intersectional settings demonstrate that FairImagen significantly improves fairness with a moderate trade-off in image quality and prompt fidelity. Our framework outperforms existing post-hoc methods and offers a simple, scalable, and model-agnostic solution for equitable text-to-image generation.

cs.LG↗

CAST: Compositional Analysis via Spectral Tracking for Understanding Transformer Layer Functions

Large language models have achieved remarkable success but remain largely black boxes with poorly understood internal mechanisms. To address this limitation, many researchers have proposed various interpretability methods including mechanistic analysis, probing classifiers, and activation visualization, each providing valuable insights from different perspectives. Building upon this rich landscape of complementary approaches, we introduce CAST (Compositional Analysis via Spectral Tracking), a probe-free framework that contributes a novel perspective by analyzing transformer layer functions through direct transformation matrix estimation and comprehensive spectral analysis. CAST offers complementary insights to existing methods by estimating the realized transformation matrices for each layer using Moore-Penrose pseudoinverse and applying spectral analysis with six interpretable metrics characterizing layer behavior. Our analysis reveals distinct behaviors between encoder-only and decoder-only models, with decoder models exhibiting compression-expansion cycles while encoder models maintain consistent high-rank processing. Kernel analysis further demonstrates functional relationship patterns between layers, with CKA similarity matrices clearly partitioning layers into three phases: feature extraction, compression, and specialization.

cs.LG↗

Multi-use LLM Watermarking and the False Detection Problem

Digital watermarking is a promising solution for mitigating some of the risks arising from the misuse of automatically generated text. These approaches either embed non-specific watermarks to allow for the detection of any text generated by a particular sampler, or embed specific keys that allow the identification of the LLM user. However, simultaneously using the same embedding for both detection and user identification leads to a false detection problem, whereby, as user capacity grows, unwatermarked text is increasingly likely to be falsely detected as watermarked. Through theoretical analysis, we identify the underlying causes of this phenomenon. Building on these insights, we propose Dual Watermarking which jointly encodes detection and identification watermarks into generated text, significantly reducing false positives while maintaining high detection accuracy. Our experimental results validate our theoretical findings and demonstrate the effectiveness of our approach.

cs.CR↗

Evaluating Model Explanations without Ground Truth

There can be many competing and contradictory explanations for a single model prediction, making it difficult to select which one to use. Current explanation evaluation frameworks measure quality by comparing against ideal "ground-truth" explanations, or by verifying model sensitivity to important inputs. We outline the limitations of these approaches, and propose three desirable principles to ground the future development of explanation evaluation strategies for local feature importance explanations. We propose a ground-truth Agnostic eXplanation Evaluation framework (AXE) for evaluating and comparing model explanations that satisfies these principles. Unlike prior approaches, AXE does not require access to ideal ground-truth explanations for comparison, or rely on model sensitivity - providing an independent measure of explanation quality. We verify AXE by comparing with baselines, and show how it can be used to detect explanation fairwashing. Our code is available at https://github.com/KaiRawal/Evaluating-Model-Explanations-without-Ground-Truth.

cs.AI↗

CLIP-SENet: CLIP-based Semantic Enhancement Network for Vehicle Re-identification

Vehicle re-identification (Re-ID) is a crucial task in intelligent transportation systems (ITS), aimed at retrieving and matching the same vehicle across different surveillance cameras. Numerous studies have explored methods to enhance vehicle Re-ID by focusing on semantic enhancement. However, these methods often rely on additional annotated information to enable models to extract effective semantic features, which brings many limitations. In this work, we propose a CLIP-based Semantic Enhancement Network (CLIP-SENet), an end-to-end framework designed to autonomously extract and refine vehicle semantic attributes, facilitating the generation of more robust semantic feature representations. Inspired by zero-shot solutions for downstream tasks presented by large-scale vision-language models, we leverage the powerful cross-modal descriptive capabilities of the CLIP image encoder to initially extract general semantic information. Instead of using a text encoder for semantic alignment, we design an adaptive fine-grained enhancement module (AFEM) to adaptively enhance this general semantic information at a fine-grained level to obtain robust semantic feature representations. These features are then fused with common Re-ID appearance features to further refine the distinctions between vehicles. Our comprehensive evaluation on three benchmark datasets demonstrates the effectiveness of CLIP-SENet. Our approach achieves new state-of-the-art performance, with 92.9% mAP and 98.7% Rank-1 on VeRi-776 dataset, 90.4% Rank-1 and 98.7% Rank-5 on VehicleID dataset, and 89.1% mAP and 97.9% Rank-1 on the more challenging VeRi-Wild dataset.

cs.CV↗