arXiv subjects

Shasha Zhou

Publications and source records attributed to Shasha Zhou.

6 recordsLinked to original sources

arXiv2026

Position: Genomic Model Research Must Move Beyond Anecdotal Evaluation of Interpretability Methods

Advances in machine learning and computational power have unlocked the predictive potential of the human genome, yet biologists now demand that these models also elucidate the underlying biological mechanisms. While interpretable machine learning (IML) techniques have been increasingly applied to bridge this gap, there has been a pervasive reliance on anecdotal validation: the vast majority of research relies on a single IML method and reports only isolated successful instances. Through a benchmarking study on transcription factor binding, we demonstrate the risks of current practices. We show that different IML methods can often (1) yield contradictory explanations for the same predictions, (2) fail to localize known regulatory motifs, and (3) fail to faithfully reflect the model's internal decision process. In light of this, we argue for a validation framework analogous to clinical trials: just as trials require rigorous design and adverse-event reporting, genomic interpretability must move beyond cherry-picked plausibility toward systematic assessment of consistency, faithfulness, and biological validity. To facilitate this, we propose a tiered framework to guide rigorous evaluation and reporting of genomic IML methods.

cs.LG↗

arXiv2025

Assessing Automated Fact-Checking for Medical LLM Responses with Knowledge Graphs

The recent proliferation of large language models (LLMs) holds the potential to revolutionize healthcare, with strong capabilities in diverse medical tasks. Yet, deploying LLMs in high-stakes healthcare settings requires rigorous verification and validation to understand any potential harm. This paper investigates the reliability and viability of using medical knowledge graphs (KGs) for the automated factuality evaluation of LLM-generated responses. To ground this investigation, we introduce FAITH, a framework designed to systematically probe the strengths and limitations of this KG-based approach. FAITH operates without reference answers by decomposing responses into atomic claims, linking them to a medical KG, and scoring them based on evidence paths. Experiments on diverse medical tasks with human subjective evaluations demonstrate that KG-grounded evaluation achieves considerably higher correlations with clinician judgments and can effectively distinguish LLMs with varying capabilities. It is also robust to textual variances. The inherent explainability of its scoring can further help users understand and mitigate the limitations of current LLMs. We conclude that while limitations exist, leveraging KGs is a prominent direction for automated factuality assessment in healthcare.

cs.LG↗

arXiv2025

Augmenting Biological Fitness Prediction Benchmarks with Landscapes Features from GraphFLA

Machine learning models increasingly map biological sequence-fitness landscapes to predict mutational effects. Effective evaluation of these models requires benchmarks curated from empirical data. Despite their impressive scales, existing benchmarks lack topographical information regarding the underlying fitness landscapes, which hampers interpretation and comparison of model performance beyond averaged scores. Here, we introduce GraphFLA, a Python framework that constructs and analyzes fitness landscapes from mutagensis data in diverse modalities (e.g., DNA, RNA, protein, and beyond) with up to millions of mutants. GraphFLA calculates 20 biologically relevant features that characterize 4 fundamental aspects of landscape topography. By applying GraphFLA to over 5,300 landscapes from ProteinGym, RNAGym, and CIS-BP, we demonstrate its utility in interpreting and comparing the performance of dozens of fitness prediction models, highlighting factors influencing model accuracy and respective advantages of different models. In addition, we release 155 combinatorially complete empirical fitness landscapes, encompassing over 2.2 million sequences across various modalities. All the codes and datasets are available at https://github.com/COLA-Laboratory/GraphFLA.

cs.LG↗

arXiv2025

Conversational Exploration of Literature Landscape with LitChat

We are living in an era of "big literature", where the volume of digital scientific publications is growing exponentially. While offering new opportunities, this also poses challenges for understanding literature landscapes, as traditional manual reviewing is no longer feasible. Recent large language models (LLMs) have shown strong capabilities for literature comprehension, yet they are incapable of offering "comprehensive, objective, open and transparent" views desired by systematic reviews due to their limited context windows and trust issues like hallucinations. Here we present LitChat, an end-to-end, interactive and conversational literature agent that augments LLM agents with data-driven discovery tools to facilitate literature exploration. LitChat automatically interprets user queries, retrieves relevant sources, constructs knowledge graphs, and employs diverse data-mining techniques to generate evidence-based insights addressing user needs. We illustrate the effectiveness of LitChat via a case study on AI4Health, highlighting its capacity to quickly navigate the users through large-scale literature landscape with data-based evidence that is otherwise infeasible with traditional means.

cs.CL↗

arXiv2024

Mapping Literature Landscapes with Data-Driven Discovery: A Case Study on MOEA/D

We are living in an era of "big literature", where scientific literature is expanding exponentially. While this growth presents new opportunities, it complicates mapping global scientific research landscapes, as manual review methods become infeasible. Recent advancements in machine learning, complex networks, and natural language processing have enabled numerous data-driven discovery methods. Building upon these tools, we introduce an end-to-end workflow for analyzing large-scale literature landscapes, LitLA. This workflow first integrates diverse publication metadata into a bibliographic knowledge graph (KG) representing the research landscape. It then offers tools for exploratory analysis of various landscape aspects. We demonstrate the effectiveness of LitLA via a case study on follow-up works of multi-objective evolutionary algorithm based on decomposition (MOEA/D). In doing so, we constructed the MOEA/D research landscape as a KG comprising over 5,400 papers, 10,000 authors, 1,600 institutions, and 78,000 keywords. With this landscape, we start with descriptive statistics and investigate prominent topics pertaining to MOEA/D and interrogate their spatial-temporal and bilateral relationships. We then map the collaboration and citation networks to reveal the community's growth over time. We further experiment whether learning on latent patterns of this landscape can hint on future research directions.

cs.NE↗

arXiv2017

On Landsberg general $(α,β)$-metrics with a conformal 1-form

In this paper, we study almost regular Landsberg general $(α,β)$-metrics in Finsler geometry. The corresponding equivalent equations are given. By solving the equations, we give the classification of Landsberg general $(α,β)$-metrics under the conditon that $β$ is closed and conformal to $α$. Under this condition, we prove that regular Landsberg general $(α,β)$-metrics must be Berwaldian when the dimension is greater than two. For the almost regular case, the classification also is given and some new non-Berwaldian Landsberg metrics are found.

math.DG↗