arXiv subjects

Nancy Chen

Publications and source records attributed to Nancy Chen.

11 recordsLinked to original sources

arXiv2026

Towards Annotation-Free Validation of MLLMs: A Vision-Language Logical Consistency Metric

Dominant accuracy evaluation might reward unwarranted guessing of Large Language Models, and it might not be applicable to novel tasks for model validation without ground-truth (gt) annotation. Based on basic logic principle, we propose a novel framework to evaluate the vision-language logical consistency of MLLMs on both sufficient and necessary cause-effect relations. We define Vision-Language Logical Consistency Metric (VL-LCM) on traditional MC-VQA tests, and recent NaturalBench tests without the need for gt annotation. Through systematic experiments on representative VL benchmark MMMU and recent VL challenges like NaturalBench, we evaluated 11 recent open-source MLLMs from 4 frontier families. Our findings reveal that, despite significant progress of recent MLLMs on accuracy, logical consistency lags behind significantly. Extensive evaluations on the correlations of VL-LCM with metrics on gt, the reliability of LCM, and the relation of VL-LCM with response distribution justify the validity and applicability of VL-LCM even without gt annotation. Our findings suggest that, beyond accuracy, logical consistency could be employed for both accuracy and reliability. VL-LCM can also be employed for MLLM selection, validation, and reliable answer justification in novel tasks without gt annotation.

cs.AI↗

arXiv2026

Explicit Logic Channel for Validation and Enhancement of MLLMs on Zero-Shot Tasks

Frontier Multimodal Large Language Models (MLLMs) exhibit remarkable capabilities in Visual-Language Comprehension (VLC) tasks. However, they are often deployed as zero-shot solution to new tasks in a black-box manner. Validating and understanding the behavior of these models become important for application to new task. We propose an Explicit Logic Channel, in parallel with the black-box model channel, to perform explicit logical reasoning for model validation, selection and enhancement. The frontier MLLM, encapsulating latent vision-language knowledge, can be considered as an Implicit Logic Channel. The proposed Explicit Logic Channel, mimicking human logical reasoning, incorporates a LLM, a VFM, and logical reasoning with probabilistic inference for factual, counterfactual, and relational reasoning over the explicit visual evidence. A Consistency Rate (CR) is proposed for cross-channel validation and model selection, even without ground-truth annotations. Additionally, cross-channel integration further improves performance in zero-shot tasks over MLLMs, grounded with explicit visual evidence to enhance trustworthiness. Comprehensive experiments conducted for two representative VLC tasks, i.e., MC-VQA and HC-REC, on three challenging benchmarks, with 11 recent open-source MLLMs from 4 frontier families. Our systematic evaluations demonstrate the effectiveness of proposed ELC and CR for model validation, selection and improvement on MLLMs with enhanced explainability and trustworthiness.

cs.AI↗

arXiv2026

Structure from rank: Rank-order coding as a bridge from sequence to structure

Understanding how structured sequence information can be represented and generalized in neural systems is key to modeling the transition from acoustic input to emergent structure. In this study, we propose a rank-order based neural network inspired by the STG-LIFG-PMC pathway, modeling the bottom-up transition from acoustic input to abstract rank representation and the top-down generation from that representation to motor execution. Building on previous work in rank coding, we first demonstrate that this model efficiently compresses input while retaining the capacity to reconstruct full utterances from partial cues, revealing emergent structure-sensitive generation process that reflects context-general representations of sensorimotor states, which are later shaped into context-specific motor plans during speech planning. We then show that the network exhibits global-level novelty detection similar to the P3B novelty wave, replicating the global-sequence-sensitive mechanism. As a supplement, we also compare the model's behavior under local (index-level) and global (rank-level) perturbations, revealing robustness to superficial variation and sensitivity to abstract structural violation, key features associated with hierarchical generalization. These results suggest that rank-order coding not only serves as a compact encoding scheme but also captures hierarchical structure in acoustic sequences.

cs.NE↗

arXiv2025

The Reward Model Selection Crisis in Personalized Alignment

Personalized alignment from preference data has focused primarily on improving personal reward model (RM) accuracy, with the implicit assumption that better preference ranking translates to better personalized behavior. However, in deployment, computational constraints necessitate inference-time adaptation such as reward-guided decoding (RGD) rather than per-user policy fine-tuning. This creates a critical but overlooked requirement: reward models must not only rank preferences accurately but also effectively guide generation. We demonstrate that standard RM accuracy fails catastrophically as a selection criterion for deployment-ready personalized rewards. We introduce policy accuracy; a metric quantifying whether RGD-adapted LLMs correctly discriminate between preferred and dispreferred responses and show that upstream RM accuracy correlates only weakly with downstream policy accuracy (Kendall's tau = 0.08--0.31). More critically, we introduce Pref-LaMP the first personalized alignment benchmark with ground-truth user completions, enabling direct behavioural evaluation. On Pref-LaMP, we expose a complete decoupling between discriminative ranking and generation metrics: methods with 20-point RM accuracy differences produce almost identical output quality, and methods with high ranking accuracy can fail to generate behaviorally aligned responses. These findings reveal that the field has been optimizing for proxy metrics that do not predict deployment performance, and that current personalized alignment methods fail to operationalize preferences into behavioral adaptation under realistic deployment constraints. In contrast, we find simple in-context learning (ICL) to be highly effective - dominating all reward-guided methods for models $\geq$3B parameters, achieving $\sim$3 point ROUGE-1 gains over the best reward method at 7B scale.

cs.AI↗

arXiv2025

Higher Embedding Dimension Creates a Stronger World Model for a Simple Sorting Task

We investigate how embedding dimension affects the emergence of an internal "world model" in a transformer trained with reinforcement learning to perform bubble-sort-style adjacent swaps. Models achieve high accuracy even with very small embedding dimensions, but larger dimensions yield more faithful, consistent, and robust internal representations. In particular, higher embedding dimensions strengthen the formation of structured internal representation and lead to better interpretability. After hundreds of experiments, we observe two consistent mechanisms: (1) the last row of the attention weight matrix monotonically encodes the global ordering of tokens; and (2) the selected transposition aligns with the largest adjacent difference of these encoded values. Our results provide quantitative evidence that transformers build structured internal world models and that model size improves representation quality in addition to end performance. We release our metrics and analyses, which can be used to probe similar algorithmic tasks.

cs.LG↗

arXiv2025

Incorporating Contextual Paralinguistic Understanding in Large Speech-Language Models

Current large speech language models (Speech-LLMs) often exhibit limitations in empathetic reasoning, primarily due to the absence of training datasets that integrate both contextual content and paralinguistic cues. In this work, we propose two approaches to incorporate contextual paralinguistic information into model training: (1) an explicit method that provides paralinguistic metadata (e.g., emotion annotations) directly to the LLM, and (2) an implicit method that automatically generates novel training question-answer (QA) pairs using both categorical and dimensional emotion annotations alongside speech transcriptions. Our implicit method boosts performance (LLM-judged) by 38.41% on a human-annotated QA benchmark, reaching 46.02% when combined with the explicit approach, showing effectiveness in contextual paralinguistic understanding. We also validate the LLM judge by demonstrating its correlation with classification metrics, providing support for its reliability.

cs.CL↗

arXiv2025

Constructions of Macaulay Posets and Macaulay Rings

A poset is Macaulay if its partial order and an additional total order interact well. Analogously, a ring is Macaulay if the partial order defined on its monomials by division interacts nicely with any total monomial order. We investigate methods of obtaining new structures through combining Macaulay rings and posets by means of certain operations inspired by topology. We examine whether these new structures retain the Macaulay property, identifying new classes of posets and rings for which the operations preserve the Macaulay property.

math.CO↗

arXiv2023

PromptSum: Parameter-Efficient Controllable Abstractive Summarization

Prompt tuning (PT), a parameter-efficient technique that only tunes the additional prompt embeddings while keeping the backbone pre-trained language model (PLM) frozen, has shown promising results in language understanding tasks, especially in low-resource scenarios. However, effective prompt design methods suitable for generation tasks such as summarization are still lacking. At the same time, summarization guided through instructions (discrete prompts) can achieve a desirable double objective of high quality and controllability in summary generation. Towards a goal of strong summarization performance under the triple conditions of parameter-efficiency, data-efficiency, and controllability, we introduce PromptSum, a method combining PT with a multi-task objective and discrete entity prompts for abstractive summarization. Our model achieves competitive ROUGE results on popular abstractive summarization benchmarks coupled with a strong level of controllability through entities, all while only tuning several orders of magnitude less parameters.

cs.CL↗

arXiv2022

Unsupervised Summarization Re-ranking

With the rise of task-specific pre-training objectives, abstractive summarization models like PEGASUS offer appealing zero-shot performance on downstream summarization tasks. However, the performance of such unsupervised models still lags significantly behind their supervised counterparts. Similarly to the supervised setup, we notice a very high variance in quality among summary candidates from these models while only one candidate is kept as the summary output. In this paper, we propose to re-rank summary candidates in an unsupervised manner, aiming to close the performance gap between unsupervised and supervised models. Our approach improves the unsupervised PEGASUS by up to 7.27% and ChatGPT by up to 6.86% relative mean ROUGE across four widely-adopted summarization benchmarks ; and achieves relative gains of 7.51% (up to 23.73% from XSum to WikiHow) averaged over 30 zero-shot transfer setups (finetuning on a dataset, evaluating on another).

cs.CL↗

arXiv2022

Taking Quantitative Genomics into the Wild

A key goal in studies of ecology and evolution is understanding the causes of phenotypic diversity in nature. Most traits of interest, such as those relating to morphology, life-history, immunity and behaviour are quantitative, and phenotypic variation is driven by the cumulative effects of genetic and environmental variation. The field of quantitative genetics aims to quantify the additive genetic component of this trait variance (i.e. the "heritability"), often with the underlying assumption that trait variance is driven by many loci of infinitesimal effects throughout the genome. This approach allows us to understand the evolutionary potential of natural populations and can be extended to examine the genetic covariation with fitness to predict responses to selection. Therefore, quantitative genetic studies are fundamental to understanding evolution in the wild. Over the last two decades, there has been a wealth of studies investigating trait heritabilities and genetic correlations, but these were initially limited to long-term studies of pedigreed populations or common-garden experiments. However, genomic technologies have since allowed quantitative genetic studies in a more diverse range of wild systems and has increased the opportunities for addressing outstanding questions in ecology and evolution. In particular, genomic studies can uncover the genetic basis of fitness-related quantitative traits, allowing a better understanding of their evolutionary dynamics. We organised this special issue to highlight new work and review recent advances at the cutting edge of "Wild Quantitative Genomics". In this Editorial, we will present some history of wild quantitative genetic and genomic studies, before discussing the main themes in the papers published in this special issue and highlighting the future outlook of this dynamic field.

q-bio.PE↗

arXiv2017

Truly Multi-modal YouTube-8M Video Classification with Video, Audio, and Text

The YouTube-8M video classification challenge requires teams to classify 0.7 million videos into one or more of 4,716 classes. In this Kaggle competition, we placed in the top 3% out of 650 participants using released video and audio features. Beyond that, we extend the original competition by including text information in the classification, making this a truly multi-modal approach with vision, audio and text. The newly introduced text data is termed as YouTube-8M-Text. We present a classification framework for the joint use of text, visual and audio features, and conduct an extensive set of experiments to quantify the benefit that this additional mode brings. The inclusion of text yields state-of-the-art results, e.g. 86.7% GAP on the YouTube-8M-Text validation dataset.

cs.CV↗