arXiv subjects

Liyan Tang

Publications and source records attributed to Liyan Tang.

14 recordsLinked to original sources

arXiv2026

WikiSkill: Compiling Agent Experience into Persistent Knowledge for Skill Evolution

Agent skills package specialized knowledge and workflows into reusable resources that extend AI agent capabilities. Recent work automatically discovers such skills from agent experience, which enables agents to progressively adapt through interaction. However, the insights that guide skill development typically remain scattered across optimization histories, limiting their systematic reuse across iterations. We introduce WikiSkill, a framework that co-evolves agent skills with a persistent knowledge base (wiki). At a high level, WikiSkill separates raw execution experience, accumulated knowledge, and executable skills, while continuously consolidating experience into the wiki, which subsequent skill updates can build on. Across diverse benchmarks and models, WikiSkill consistently outperforms state-of-the-art skill-evolution methods and improves over no-skill baselines in most model-benchmark settings. We find that skill evolution complements model scaling: larger models generally benefit more from evolved skills, while smaller models with skills can outperform substantially larger models without them. We also find that evolved skills transfer effectively across models and model families, and skills evolved by other models can outperform self-evolved skills. Finally, our ablation studies confirm that persistent knowledge accumulation in the wiki is critical for effective skill evolution. These results demonstrate the benefits of systematically accumulating and refining agent experience for developing reusable and transferable skills.

cs.AI↗

arXiv2026

Visually Grounded Self-Reflection for Vision-Language Models via Reinforcement Learning

Large vision-language models can reason over multimodal inputs by generating textual chains of thought (CoT). A key capability exhibited in CoT reasoning is self-reflection: revisiting earlier decisions and correcting previous errors. However, existing LVLMs often fail to properly attend to visual inputs during reflection, limiting their ability to translate feedback into grounded corrections, especially for out-of-distribution images. To address this issue, we propose a novel reinforcement learning training framework VRRL, with two components explicitly designed to elicit visually grounded self-reflection. First, we randomly mask trajectory prefixes during training to emphasize recovery from incorrect intermediate predictions rather than making early mistakes. Second, we introduce buffered roll-ins from an experience replay buffer to expose the model to diverse failure states that it must learn to correct. We evaluate our approach on visual grounding tasks involving tables and charts, as well as spatial navigation benchmarks. While off-the-shelf and conventionally fine-tuned models degrade substantially under distribution shift, our method substantially improves average out-of-distribution accuracy over standard RL and reflection-oriented fine-tuning baselines by using self-reflection effectively.

cs.CL↗

arXiv2025

A Liquid-Nitrogen-Cooled Ca+ Ion Optical Clock with a Systematic Uncertainty of 4.4E-19

We report a single-ion optical clock based on the 4S_1/2-3D_5/2 transition of the 40Ca+ ion, operated in a liquid nitrogen cryogenic environment,achieving a total systematic uncertainty of 4.4E-19. We employ a refined temperature evaluation scheme to reduce the frequency uncertainty due to blackbody radiation (BBR), and the 3D sideband cooling has been implemented to minimize the second-order Doppler shift. We have precisely determined the average Zeeman coefficient of the 40Ca+ clock transition to be 14.345(40) Hz/mT^2, thereby significantly reducing the quadratic Zeeman shift uncertainty. Moreover, the cryogenic environment enables the lowest reported heating rate due to ambient electric field noise in trapped-ion optical clocks.

physics.atom-ph↗

arXiv2025

ChartMuseum: Testing Visual Reasoning Capabilities of Large Vision-Language Models

Chart understanding presents a unique challenge for large vision-language models (LVLMs), as it requires the integration of sophisticated textual and visual reasoning capabilities. However, current LVLMs exhibit a notable imbalance between these skills, falling short on visual reasoning that is difficult to perform in text. We conduct a case study using a synthetic dataset solvable only through visual reasoning and show that model performance degrades significantly with increasing visual complexity, while human performance remains robust. We then introduce ChartMuseum, a new Chart Question Answering (QA) benchmark containing 1,162 expert-annotated questions spanning multiple reasoning types, curated from real-world charts across 184 sources, specifically built to evaluate complex visual and textual reasoning. Unlike prior chart understanding benchmarks -- where frontier models perform similarly and near saturation -- our benchmark exposes a substantial gap between model and human performance, while effectively differentiating model capabilities: although humans achieve 93% accuracy, the best-performing model Gemini-2.5-Pro attains only 63.0%, and the leading open-source LVLM Qwen2.5-VL-72B-Instruct achieves only 38.5%. Moreover, on questions requiring primarily visual reasoning, all models experience a 35%-55% performance drop from text-reasoning-heavy question performance. Lastly, our qualitative error analysis reveals specific categories of visual reasoning that are challenging for current LVLMs.

cs.CL↗

arXiv2025

Is the Top Still Spinning? Evaluating Subjectivity in Narrative Understanding

Determining faithfulness of a claim to a source document is an important problem across many domains. This task is generally treated as a binary judgment of whether the claim is supported or unsupported in relation to the source. In many cases, though, whether a claim is supported can be ambiguous. For instance, it may depend on making inferences from given evidence, and different people can reasonably interpret the claim as either supported or unsupported based on their agreement with those inferences. Forcing binary labels upon such claims lowers the reliability of evaluation. In this work, we reframe the task to manage the subjectivity involved with factuality judgments of ambiguous claims. We introduce LLM-generated edits of summaries as a method of providing a nuanced evaluation of claims: how much does a summary need to be edited to be unambiguous? Whether a claim gets rewritten and how much it changes can be used as an automatic evaluation metric, the Ambiguity Rewrite Metric (ARM), with a much richer feedback signal than a binary judgment of faithfulness. We focus on the area of narrative summarization as it is particularly rife with ambiguity and subjective interpretation. We show that ARM produces a 21% absolute improvement in annotator agreement on claim faithfulness, indicating that subjectivity is reduced.

cs.CL↗

arXiv2024

MiniCheck: Efficient Fact-Checking of LLMs on Grounding Documents

Recognizing if LLM output can be grounded in evidence is central to many tasks in NLP: retrieval-augmented generation, summarization, document-grounded dialogue, and more. Current approaches to this kind of fact-checking are based on verifying each piece of a model generation against potential evidence using an LLM. However, this process can be very computationally expensive, requiring many calls to a model to check a single response. In this work, we show how to build small fact-checking models that have GPT-4-level performance but for 400x lower cost. We do this by constructing synthetic training data with GPT-4, which involves creating realistic yet challenging instances of factual errors via a structured generation procedure. Training on this data teaches models to check each fact in the claim and recognize synthesis of information across sentences. For evaluation, we unify datasets from recent work on fact-checking and grounding LLM generations into a new benchmark, LLM-AggreFact. Our best system MiniCheck-FT5 (770M parameters) outperforms all systems of comparable size and reaches GPT-4 accuracy. We release LLM-AggreFact, code for data synthesis, and models.

cs.CL↗

arXiv2024

TofuEval: Evaluating Hallucinations of LLMs on Topic-Focused Dialogue Summarization

Single document news summarization has seen substantial progress on faithfulness in recent years, driven by research on the evaluation of factual consistency, or hallucinations. We ask whether these advances carry over to other text summarization domains. We propose a new evaluation benchmark on topic-focused dialogue summarization, generated by LLMs of varying sizes. We provide binary sentence-level human annotations of the factual consistency of these summaries along with detailed explanations of factually inconsistent sentences. Our analysis shows that existing LLMs hallucinate significant amounts of factual errors in the dialogue domain, regardless of the model's size. On the other hand, when LLMs, including GPT-4, serve as binary factual evaluators, they perform poorly and can be outperformed by prevailing state-of-the-art specialized factuality evaluation metrics. Finally, we conducted an analysis of hallucination types with a curated error taxonomy. We find that there are diverse errors and error distributions in model-generated summaries and that non-LLM based metrics can capture all error types better than LLM-based evaluators.

cs.CL↗

arXiv2023

Less Likely Brainstorming: Using Language Models to Generate Alternative Hypotheses

A human decision-maker benefits the most from an AI assistant that corrects for their biases. For problems such as generating interpretation of a radiology report given findings, a system predicting only highly likely outcomes may be less useful, where such outcomes are already obvious to the user. To alleviate biases in human decision-making, it is worth considering a broad differential diagnosis, going beyond the most likely options. We introduce a new task, "less likely brainstorming," that asks a model to generate outputs that humans think are relevant but less likely to happen. We explore the task in two settings: a brain MRI interpretation generation setting and an everyday commonsense reasoning setting. We found that a baseline approach of training with less likely hypotheses as targets generates outputs that humans evaluate as either likely or irrelevant nearly half of the time; standard MLE training is not effective. To tackle this problem, we propose a controlled text generation method that uses a novel contrastive learning strategy to encourage models to differentiate between generating likely and less likely outputs according to humans. We compare our method with several state-of-the-art controlled text generation models via automatic and human evaluations and show that our models' capability of generating less likely outputs is improved.

cs.CL↗

arXiv2022

Understanding Factual Errors in Summarization: Errors, Summarizers, Datasets, Error Detectors

The propensity of abstractive summarization models to make factual errors has been studied extensively, including design of metrics to detect factual errors and annotation of errors in current systems' outputs. However, the ever-evolving nature of summarization systems, metrics, and annotated benchmarks makes factuality evaluation a moving target, and drawing clear comparisons among metrics has become increasingly difficult. In this work, we aggregate factuality error annotations from nine existing datasets and stratify them according to the underlying summarization model. We compare performance of state-of-the-art factuality metrics, including recent ChatGPT-based metrics, on this stratified benchmark and show that their performance varies significantly across different types of summarization models. Critically, our analysis shows that much of the recent improvement in the factuality detection space has been on summaries from older (pre-Transformer) models instead of more relevant recent summarization models. We further perform a finer-grained analysis per error-type and find similar performance variance across error types for different factuality metrics. Our results show that no one metric is superior in all settings or for all error types, and we provide recommendations for best practices given these insights.

cs.CL↗

arXiv2022

Measurement of infrared magic wavelength for an all-optical trapping of $^{40}$Ca$^{+}$ ion clock

For the first time, we experimentally determine the infrared magic wavelength for the $^{40}$Ca$^{+}$ $4s\, ^{2}\!S_{1/2} \rightarrow 3d\,^{2}\!D_{5/2}$ electric quadrupole transition by observation of the light shift canceling in $^{40}$Ca$^{+}$ optical clock. A "magic" magnetic field direction is chosen to make the magic wavelength insensitive to both the linear polarization purity and the polarization direction of the laser. The determined magic wavelength for this transition is 1056.37(9)~nm, which is not only in good agreement with theoretical predictions but also more precise by a factor of about 300. Using this measured magic wavelength we also derive the differential static polarizability to be $-44.32(32)$~a.u., which will be an important input for the evaluation of the blackbody radiation shift at room temperatures. Our work paves a way for all-optical-trapping of $^{40}$Ca$^{+}$ optical clock.

physics.atom-ph↗

arXiv2022

Prior Knowledge Enhances Radiology Report Generation

Radiology report generation aims to produce computer-aided diagnoses to alleviate the workload of radiologists and has drawn increasing attention recently. However, previous deep learning methods tend to neglect the mutual influences between medical findings, which can be the bottleneck that limits the quality of generated reports. In this work, we propose to mine and represent the associations among medical findings in an informative knowledge graph and incorporate this prior knowledge with radiology report generation to help improve the quality of generated reports. Experiment results demonstrate the superior performance of our proposed method on the IU X-ray dataset with a ROUGE-L of 0.384$\pm$0.007 and CIDEr of 0.340$\pm$0.011. Compared with previous works, our model achieves an average of 1.6% improvement (2.0% and 1.5% improvements in CIDEr and ROUGE-L, respectively). The experiments suggest that prior knowledge can bring performance gains to accurate radiology report generation. We will make the code publicly available at https://github.com/bionlplab/report_generation_amia2022.

cs.CL↗

arXiv2021

RadBERT-CL: Factually-Aware Contrastive Learning For Radiology Report Classification

Radiology reports are unstructured and contain the imaging findings and corresponding diagnoses transcribed by radiologists which include clinical facts and negated and/or uncertain statements. Extracting pathologic findings and diagnoses from radiology reports is important for quality control, population health, and monitoring of disease progress. Existing works, primarily rely either on rule-based systems or transformer-based pre-trained model fine-tuning, but could not take the factual and uncertain information into consideration, and therefore generate false-positive outputs. In this work, we introduce three sedulous augmentation techniques which retain factual and critical information while generating augmentations for contrastive learning. We introduce RadBERT-CL, which fuses these information into BlueBert via a self-supervised contrastive loss. Our experiments on MIMIC-CXR show superior performance of RadBERT-CL on fine-tuning for multi-class, multi-label report classification. We illustrate that when few labeled data are available, RadBERT-CL outperforms conventional SOTA transformers (BERT/BlueBert) by significantly larger margins (6-11%). We also show that the representations learned by RadBERT-CL can capture critical medical information in the latent space.

cs.LG↗

arXiv2021

Making Document-Level Information Extraction Right for the Right Reasons

Document-level models for information extraction tasks like slot-filling are flexible: they can be applied to settings where information is not necessarily localized in a single sentence. For example, key features of a diagnosis in a radiology report may not be explicitly stated in one place, but nevertheless can be inferred from parts of the report's text. However, these models can easily learn spurious correlations between labels and irrelevant information. This work studies how to ensure that these models make correct inferences from complex text and make those inferences in an auditable way: beyond just being right, are these models "right for the right reasons?" We experiment with post-hoc evidence extraction in a predict-select-verify framework using feature attribution techniques. We show that regularization with small amounts of evidence supervision during training can substantially improve the quality of extracted evidence. We evaluate on two domains: a small-scale labeled dataset of brain MRI reports and a large-scale modified version of DocRED (Yao et al., 2019) and show that models' plausibility can be improved with no loss in accuracy.

cs.CL↗

arXiv2020

Using Radiomics as Prior Knowledge for Thorax Disease Classification and Localization in Chest X-rays

Chest X-ray becomes one of the most common medical diagnoses due to its noninvasiveness. The number of chest X-ray images has skyrocketed, but reading chest X-rays still have been manually performed by radiologists, which creates huge burnouts and delays. Traditionally, radiomics, as a subfield of radiology that can extract a large number of quantitative features from medical images, demonstrates its potential to facilitate medical imaging diagnosis before the deep learning era. In this paper, we develop an end-to-end framework, ChexRadiNet, that can utilize the radiomics features to improve the abnormality classification performance. Specifically, ChexRadiNet first applies a light-weight but efficient triplet-attention mechanism to classify the chest X-rays and highlight the abnormal regions. Then it uses the generated class activation map to extract radiomic features, which further guides our model to learn more robust image features. After a number of iterations and with the help of radiomic features, our framework can converge to more accurate image regions. We evaluate the ChexRadiNet framework using three public datasets: NIH ChestX-ray, CheXpert, and MIMIC-CXR. We find that ChexRadiNet outperforms the state-of-the-art on both disease detection (0.843 in AUC) and localization (0.679 in T(IoU) = 0.1). We will make the code publicly available at https://github.com/bionlplab/lung_disease_detection_amia2021, with the hope that this method can facilitate the development of automatic systems with a higher-level understanding of the radiological world.

cs.CV↗