Yangxinyu Xie

Mario Krenn, Lorenzo Buffoni, Bruno Coutinho et al.

A tool that could suggest new personalized research directions and ideas by taking insights from the scientific literature could significantly accelerate the progress of science. A field that might benefit from such an approach is artificial intelligence (AI) research, where the number of scientific publications has been growing exponentially over the last years, making it challenging for human researchers to keep track of the progress. Here, we use AI techniques to predict the future research directions of AI itself. We develop a new graph-based benchmark based on real-world data -- the Science4Cast benchmark, which aims to predict the future state of an evolving semantic network of AI. For that, we use more than 100,000 research papers and build up a knowledge network with more than 64,000 concept nodes. We then present ten diverse methods to tackle this task, ranging from pure statistical to pure learning methods. Surprisingly, the most powerful methods use a carefully curated set of network features, rather than an end-to-end AI approach. It indicates a great potential that can be unleashed for purely ML approaches without human knowledge. Ultimately, better predictions of new future research directions will be a crucial component of more advanced research suggestion tools.

James Alcala, Rayna Andreeva, Vladimir A. Kobzar et al.

When training a neural network for classification, the feature vectors of the training set are known to collapse to the vertices of a regular simplex, provided the dimension $d$ of the feature space and the number $n$ of classes satisfies $n\leq d+1$. This phenomenon is known as neural collapse. For other applications like language models, one instead takes $n\gg d$. Here, the neural collapse phenomenon still occurs, but with different emergent geometric figures. We characterize these geometric figures in the orthoplex regime where $d+2\leq n\leq 2d$. The techniques in our analysis primarily involve Radon's theorem and convexity.

Yangxinyu Xie, Tanwi Mallick

Spatiotemporal graph neural networks have achieved state-of-the-art performance in traffic forecasting. However, they often struggle to forecast congestion accurately due to the limitations of traditional loss functions. While accurate forecasting of regular traffic conditions is crucial, a reliable AI system must also accurately forecast congestion scenarios to maintain safe and efficient transportation. In this paper, we explore various loss functions inspired by heavy tail analysis and imbalanced classification problems to address this issue. We evaluate the efficacy of these loss functions in forecasting traffic speed, with an emphasis on congestion scenarios. Through extensive experiments on real-world traffic datasets, we discovered that when optimizing for Mean Absolute Error (MAE), the MAE-Focal Loss function stands out as the most effective. When optimizing Mean Squared Error (MSE), Gumbel Loss proves to be the superior choice. These choices effectively forecast traffic congestion events without compromising the accuracy of regular traffic speed forecasts. This research enhances deep learning models' capabilities in forecasting sudden speed changes due to congestion and underscores the need for more research in this direction. By elevating the accuracy of congestion forecasting, we advocate for AI systems that are reliable, secure, and resilient in practical traffic management scenarios.

Homaira Huda Shomee, Rochana Chaturvedi, Yangxinyu Xie et al.

Large language models (LLMs) are increasingly used to support question answering and decision-making in high-stakes, domain-specific settings such as natural hazard response and infrastructure planning, where effective answers must convey fine-grained, decision-critical details. However, existing evaluation frameworks for retrieval-augmented generation (RAG) and open-ended question answering primarily rely on surface-level similarity, factual consistency, or semantic relevance, and often fail to assess whether responses provide the specific information required for domain-sensitive decisions. To address this gap, we propose a multi-dimensional, reference-free evaluation framework that assesses LLM outputs along four complementary dimensions: specificity, robustness to paraphrasing and semantic perturbations, answer relevance, and context utilization. We introduce a curated dataset of 1,412 domain-specific question-answer pairs spanning 40 professional roles and seven natural hazard types to support systematic evaluation. We further conduct human evaluation to assess inter-annotator agreement and alignment between model outputs and human judgments, which highlights the inherent subjectivity of open-ended, domain-specific evaluation. Our results show that no single metric sufficiently captures answer quality in isolation and demonstrate the need for structured, multi-metric evaluation frameworks when deploying LLMs in high-stakes applications.

Bowen Jiang, Yangxinyu Xie, Zhuoqun Hao et al.

This study introduces a hypothesis-testing framework to assess whether large language models (LLMs) possess genuine reasoning abilities or primarily depend on token bias. We go beyond evaluating LLMs on accuracy; rather, we aim to investigate their token bias in solving logical reasoning tasks. Specifically, we develop carefully controlled synthetic datasets, featuring conjunction fallacy and syllogistic problems. Our framework outlines a list of hypotheses where token biases are readily identifiable, with all null hypotheses assuming genuine reasoning capabilities of LLMs. The findings in this study suggest, with statistical guarantee, that most LLMs still struggle with logical reasoning. While they may perform well on classic problems, their success largely depends on recognizing superficial patterns with strong token bias, thereby raising concerns about their actual reasoning and generalization abilities. Codes and data are open-sourced at https://github.com/bowen-upenn/llm_token_bias.

Bowen Jiang, Yangxinyu Xie, Xiaomeng Wang et al.

This work discusses how to build more rational language and multimodal agents and what criteria define rationality in intelligent systems. Rationality is the quality of being guided by reason, characterized by decision-making that aligns with evidence and logical principles. It plays a crucial role in reliable problem-solving by ensuring well-grounded and consistent solutions. Despite their progress, large language models (LLMs) often fall short of rationality due to their bounded knowledge space and inconsistent outputs. In response, recent efforts have shifted toward developing multimodal and multi-agent systems, as well as integrating modules like external tools, programming codes, symbolic reasoners, utility function, and conformal risk controls rather than relying solely on a single LLM for decision-making. This paper surveys state-of-the-art advancements in language and multimodal agents, assesses their role in enhancing rationality, and outlines open challenges and future research directions. We maintain an open repository at https://github.com/bowen-upenn/Agent_Rationality.

Yangxinyu Xie, Bowen Jiang, Tanwi Mallick et al.

Recent advancement of large language models (LLMs) represents a transformational capability at the frontier of artificial intelligence. However, LLMs are generalized models, trained on extensive text corpus, and often struggle to provide context-specific information, particularly in areas requiring specialized knowledge, such as wildfire details within the broader context of climate change. For decision-makers focused on wildfire resilience and adaptation, it is crucial to obtain responses that are not only precise but also domain-specific. To that end, we developed WildfireGPT, a prototype LLM agent designed to transform user queries into actionable insights on wildfire risks. We enrich WildfireGPT by providing additional context, such as climate projections and scientific literature, to ensure its information is current, relevant, and scientifically accurate. This enables WildfireGPT to be an effective tool for delivering detailed, user-specific insights on wildfire risks to support a diverse set of end users, including but not limited to researchers and engineers, for making positive impact and decision making.

Georgy Noarov, Soham Mallick, Tao Wang et al.

Top-$k$ decoding is a widely used method for sampling from LLMs: at each token, only the largest $k$ next-token-probabilities are kept, and the next token is sampled after re-normalizing them to sum to unity. Top-$k$ and other sampling methods are motivated by the intuition that true next-token distributions are sparse, and the noisy LLM probabilities need to be truncated. However, to our knowledge, a precise theoretical motivation for the use of top-$k$ decoding is missing. In this work, we develop a theoretical framework that both explains and generalizes top-$k$ decoding. We view decoding at a fixed token as the recovery of a sparse probability distribution. We consider \emph{Bregman decoders} obtained by minimizing a separable Bregman divergence (for both the \emph{primal} and \emph{dual} cases) with a sparsity-inducing $\ell_0$ regularization. Despite the combinatorial nature of the objective, we show how to optimize it efficiently for a large class of divergences. We show that the optimal decoding strategies are greedy, and further that the loss function is discretely convex in $k$, so that binary search provably and efficiently finds the optimal $k$. We show that top-$k$ decoding arises as a special case for the KL divergence, and identify new decoding strategies that have distinct behaviors (e.g., non-linearly up-weighting larger probabilities after re-normalization).

Yangxinyu Xie, Bowen Jiang, Tanwi Mallick et al.

Large language models (LLMs) are a transformational capability at the frontier of artificial intelligence and machine learning that can support decision-makers in addressing pressing societal challenges such as extreme natural hazard events. As generalized models, LLMs often struggle to provide context-specific information, particularly in areas requiring specialized knowledge. In this work we propose a retrieval-augmented generation (RAG)-based multi-agent LLM system to support analysis and decision-making in the context of natural hazards and extreme weather events. As a proof of concept, we present WildfireGPT, a specialized system focused on wildfire hazards. The architecture employs a user-centered, multi-agent design to deliver tailored risk insights across diverse stakeholder groups. By integrating natural hazard and extreme weather projection data, observational datasets, and scientific literature through an RAG framework, the system ensures both the accuracy and contextual relevance of the information it provides. Evaluation across ten expert-led case studies demonstrates that WildfireGPT significantly outperforms existing LLM-based solutions for decision support.

Yangxinyu Xie, Xiang Li, Tanwi Mallick et al.

Watermarking language models is essential for distinguishing between human and machine-generated text and thus maintaining the integrity and trustworthiness of digital communication. We present a novel green/red list watermarking approach that partitions the token set into ``green'' and ``red'' lists, subtly increasing the generation probability for green tokens. To correct token distribution bias, our method employs maximal coupling, using a uniform coin flip to decide whether to apply bias correction, with the result embedded as a pseudorandom watermark signal. Theoretical analysis confirms this approach's unbiased nature and robust detection capabilities. Experimental results show that it outperforms prior techniques by preserving text quality while maintaining high detectability, and it demonstrates resilience to targeted modifications aimed at improving text quality. This research provides a promising watermarking solution for language models, balancing effective detection with minimal impact on text quality.

Yangxinyu Xie, Tao Wang, Soham Mallick et al.

While LLMs have seen substantial improvement in reasoning capabilities, they also sometimes overthink, generating unnecessary reasoning steps, particularly under uncertainty, given ill-posed or ambiguous queries. We introduce statistically principled early stopping methods that monitor uncertainty signals during generation to mitigate this issue. Our first approach is parametric: it models inter-arrival times of uncertainty keywords as a renewal process and applies sequential testing for stopping. Our second approach is nonparametric and provides finite-sample guarantees on the probability of halting too early on well-posed queries. We conduct empirical evaluations on reasoning tasks across several domains and models. Our results indicate that uncertainty-aware early stopping can improve both efficiency and reliability in LLM reasoning, and we observe especially significant gains for math reasoning.

Bowen Jiang, Yangxinyu Xie, Xiaomeng Wang et al.

We present GeoGrid-Bench, a benchmark designed to evaluate the ability of foundation models to understand geo-spatial data in the grid structure. Geo-spatial datasets pose distinct challenges due to their dense numerical values, strong spatial and temporal dependencies, and unique multimodal representations including tabular data, heatmaps, and geographic visualizations. To assess how foundation models can support scientific research in this domain, GeoGrid-Bench features large-scale, real-world data covering 16 climate variables across 150 locations and extended time frames. The benchmark includes approximately 3,200 question-answer pairs, systematically generated from 8 domain expert-curated templates to reflect practical tasks encountered by human scientists. These range from basic queries at a single location and time to complex spatiotemporal comparisons across regions and periods. Our evaluation reveals that vision-language models perform best overall, and we provide a fine-grained analysis of the strengths and limitations of different foundation models in different geo-spatial tasks. This benchmark offers clearer insights into how foundation models can be effectively applied to geo-spatial data analysis and used to support scientific research.

Akash Dhruv, Yangxinyu Xie, Jordan Branham et al.

This paper presents a comparative study of large language models (LLMs) in interpreting grid-structured geospatial data. We evaluate the performance of a base model through structured prompting and contrast it with a fine-tuned variant trained on a dataset of user-assistant interactions. Our results highlight the strengths and limitations of zero-shot prompting and demonstrate the benefits of fine-tuning for structured geospatial and temporal reasoning.

Ngoc Mai Tran, Yangxinyu Xie

The Science4cast Competition consists of predicting new links in a semantic network, with each node representing a concept and each edge representing a link proposed by a paper relating two concepts. This network contains information from 1994-2017, with a discretization of days (which represents the publication date of the underlying papers). Team Hash Brown's final submission, \emph{ee5a}, achieved a score of 0.92738 on the test set. Our team's score ranks \emph{second place}, 0.01 below the winner's score. This paper details our model, its intuition, and the performance of its variations in the test set.