Leon Bergen

Jianyou Wang, Kaicheng Wang, Xiaoyue Wang et al.

In scientific research, the ability to effectively retrieve relevant documents based on complex, multifaceted queries is critical. Existing evaluation datasets for this task are limited, primarily due to the high cost and effort required to annotate resources that effectively represent complex queries. To address this, we propose a novel task, Scientific DOcument Retrieval using Multi-level Aspect-based quEries (DORIS-MAE), which is designed to handle the complex nature of user queries in scientific research. We developed a benchmark dataset within the field of computer science, consisting of 100 human-authored complex query cases. For each complex query, we assembled a collection of 100 relevant documents and produced annotated relevance scores for ranking them. Recognizing the significant labor of expert annotation, we also introduce Anno-GPT, a scalable framework for validating the performance of Large Language Models (LLMs) on expert-level dataset annotation tasks. LLM annotation of the DORIS-MAE dataset resulted in a 500x reduction in cost, without compromising quality. Furthermore, due to the multi-tiered structure of these complex queries, the DORIS-MAE dataset can be extended to over 4,000 sub-query test cases without requiring additional annotation. We evaluated 17 recent retrieval methods on DORIS-MAE, observing notable performance drops compared to traditional datasets. This highlights the need for better approaches to handle complex, multifaceted queries in scientific research. Our dataset and codebase are available at https://github.com/Real-Doris-Mae/Doris-Mae-Dataset.

Jianyou Wang, Youze Zheng, Longtian Bao et al.

Scientists have long sought to accurately predict outcomes of real-world events before they happen. Can AI systems do so more reliably? We study this question through clinical trial outcome prediction, a high-stakes open challenge even for domain experts. We introduce CT Open, an open-access, live platform that will run four challenge every year. Anyone can submit predictions for each challenge. CT Open evaluates those submissions on trials whose outcomes were not yet public at the time of submission but were made public afterwards. Determining if a trial's outcome is public on the internet before a certain date is surprisingly difficult. Outcomes posted on official registries may lag behind by years, while the first mention may appear in obscure articles. To address this, we propose a novel, fully automated decontamination pipeline that uses iterative LLM-powered web search to identify the earliest mention of trial outcomes. We validate the pipeline's quality and accuracy by human expert's annotations. Since CT Open's pipeline ensures that every evaluated trial had no publicly reported outcome when the prediction was made, it allows participants to use any methodology and any data source. In this paper, we release a training set and two time-stamped test benchmarks, Winter 2025 and Summer 2025. We believe CT Open can serve as a central hub for advancing AI research on forecasting real-world outcomes before they occur, while also informing biomedical research and improving clinical trial design. CT Open Platform is hosted at $\href{https://ct-open.net/}{https://ct-open.net/}$

Bohan Lyu, Yadi Cao, Duncan Watson-Parris et al.

Large Language Models (LLMs) demonstrate promising capabilities in solving scientific problems but often suffer from the issue of hallucination. While integrating LLMs with tools can mitigate this issue, models fine-tuned on tool usage become overreliant on them and incur unnecessary costs. Inspired by how human experts assess problem complexity before selecting solutions, we propose a novel two-component fine-tuning method, Adapting While Learning (AWL). In the first component, World Knowledge Learning (WKL), LLMs internalize scientific knowledge by learning from tool-generated solutions. In the second component, Tool Usage Adaptation (TUA), we categorize problems as easy or hard based on the model's accuracy, and train it to maintain direct reasoning for easy problems while switching to tools for hard ones. We validate our method on six scientific benchmark datasets across climate science, epidemiology, physics, and other domains. Compared to the original instruct model (8B), models post-trained with AWL achieve 29.11% higher answer accuracy and 12.72% better tool usage accuracy, even surpassing state-of-the-art models including GPT-4o and Claude-3.5 on four custom-created datasets. Our code is open-source at https://github.com/Rose-STL-Lab/Adapting-While-Learning.

Veeramakali Vignesh Manivannan, Yasaman Jafari, Srikar Eranky et al.

The use of Large Language Models (LLMs) in climate science has recently gained significant attention. However, a critical issue remains: the lack of a comprehensive evaluation framework capable of assessing the quality and scientific validity of model outputs. To address this issue, we develop ClimaGen (Climate QA Generator), an adaptive learning framework that generates question-answer pairs from graduate textbooks with climate scientists in the loop. As a result, we present ClimaQA-Gold, an expert-annotated benchmark dataset alongside ClimaQA-Silver, a large-scale, comprehensive synthetic QA dataset for climate science. Finally, we develop evaluation strategies and compare different LLMs on our benchmarks. Our results offer novel insights into various approaches used to enhance knowledge of climate LLMs. The source code is publicly available at https://github.com/Rose-STL-Lab/genie-climaqa

Jianyou Wang, Kaicheng Wang, Xiaoyue Wang et al.

Effective information retrieval (IR) in settings with limited training data, particularly for complex queries, remains a challenging task. This paper introduces IR2, Information Regularization for Information Retrieval, a technique for reducing overfitting during synthetic data generation. This approach, representing a novel application of regularization techniques in synthetic data creation for IR, is tested on three recent IR tasks characterized by complex queries: DORIS-MAE, ArguAna, and WhatsThatBook. Experimental results indicate that our regularization techniques not only outperform previous synthetic query generation methods on the tasks considered but also reduce cost by up to 50%. Furthermore, this paper categorizes and explores three regularization methods at different stages of the query synthesis pipeline-input, prompt, and output-each offering varying degrees of performance improvement compared to models where no regularization is applied. This provides a systematic approach for optimizing synthetic data generation in data-limited, complex-query IR scenarios. All code, prompts and synthetic data are available at https://github.com/Info-Regularization/Information-Regularization.

Jianyou Wang, Weili Cao, Kaicheng Wang et al.

We study the task of automatically finding evidence relevant to hypotheses in biomedical papers. Finding relevant evidence is an important step when researchers investigate scientific hypotheses. We introduce EvidenceBench to measure models performance on this task, which is created by a novel pipeline that consists of hypothesis generation and sentence-by-sentence annotation of biomedical papers for relevant evidence, completely guided by and faithfully following existing human experts judgment. We demonstrate the pipeline's validity and accuracy with multiple sets of human-expert annotations. We evaluated a diverse set of language models and retrieval systems on the benchmark and found that model performances still fall significantly short of the expert level on this task. To show the scalability of our proposed pipeline, we create a larger EvidenceBench-100k with 107,461 fully annotated papers with hypotheses to facilitate model training and development. Both datasets are available at https://github.com/EvidenceBench/EvidenceBench

Weili Cao, Jianyou Wang, Youze Zheng et al.

Handling extremely large documents for question answering is challenging: chunk-based embedding methods often lose track of important global context, while full-context transformers can be prohibitively expensive for hundreds of thousands of tokens. We propose a single-pass document scanning approach that processes the entire text in linear time, preserving global coherence while deciding which sentences are most relevant to the query. On 41 QA benchmarks, our single-pass scanner consistently outperforms chunk-based embedding methods and competes with large language models at a fraction of the computational cost. By conditioning on the entire preceding context without chunk breaks, the method preserves global coherence, which is especially important for long documents. Overall, single-pass document scanning offers a simple solution for question answering over massive text. All code, datasets, and model checkpoints are available at https://github.com/MambaRetriever/MambaRetriever

Jianyou Wang, Weili Cao, Longtian Bao et al.

Systems that answer questions by reviewing the scientific literature are becoming increasingly feasible. To draw reliable conclusions, these systems should take into account the quality of available evidence from different studies, placing more weight on studies that use a valid methodology. We present a benchmark for measuring the methodological strength of biomedical papers, drawing on the risk-of-bias framework used for systematic reviews. Derived from over 500 biomedical studies, the three benchmark tasks encompass expert reviewers' judgments of studies' research methodologies, including the assessments of risk of bias within these studies. The benchmark contains a human-validated annotation pipeline for fine-grained alignment of reviewers' judgments with research paper sentences. Our analyses show that large language models' reasoning and retrieval capabilities impact their effectiveness with risk-of-bias assessment. The dataset is available at https://github.com/RoBBR-Benchmark/RoBBR.

Evelyn Yee, Alice Li, Chenyu Tang et al.

Large language models (LLMs) often improve their performance in downstream tasks when they generate Chain of Thought reasoning text before producing an answer. We investigate how LLMs recover from errors in Chain of Thought. Through analysis of error recovery behaviors, we find evidence for unfaithfulness in Chain of Thought, which occurs when models arrive at the correct answer despite invalid reasoning text. We identify factors that shift LLM recovery behavior: LLMs recover more frequently from obvious errors and in contexts that provide more evidence for the correct answer. Critically, these factors have divergent effects on faithful and unfaithful recoveries. Our results indicate that there are distinct mechanisms driving faithful and unfaithful error recoveries. Selective targeting of these mechanisms may be able to drive down the rate of unfaithful reasoning and improve model interpretability.

Xiaoyue Wang, Jianyou Wang, Weili Cao et al.

We present the Benchmark of Information Retrieval (IR) tasks with Complex Objectives (BIRCO). BIRCO evaluates the ability of IR systems to retrieve documents given multi-faceted user objectives. The benchmark's complexity and compact size make it suitable for evaluating large language model (LLM)-based information retrieval systems. We present a modular framework for investigating factors that may influence LLM performance on retrieval tasks, and identify a simple baseline model which matches or outperforms existing approaches and more complex alternatives. No approach achieves satisfactory performance on all benchmark tasks, suggesting that stronger models and new retrieval protocols are necessary to address complex user needs.

Yasaman Jafari, Zixian Wang, Leon Bergen et al.

We investigate whether hidden states from Structured State Space Models (SSMs) can be merged post-hoc to support downstream reasoning. Inspired by model souping, we propose a strategy where documents are encoded independently and their representations are pooled -- via simple operations like averaging -- into a single context state. This approach, which we call document souping, enables modular encoding and reuse without reprocessing the full input for each query. We finetune Mamba2 models to produce soupable representations and find that they support multi-hop QA, sparse retrieval, and long-document reasoning with strong accuracy. On HotpotQA, souping ten independently encoded documents nearly matches the performance of a cross-encoder trained on the same inputs.

Prudhviraj Naidu, Zixian Wang, Leon Bergen et al.

We train Transformer-based language models on ten foundational algorithmic tasks and observe pronounced phase transitions in their loss curves that deviate from established power-law scaling trends. Over large ranges of compute, the validation loss barely improves, then abruptly decreases. Probing the models' internal representations reveals that quiet features are learned prior to any decrease in task loss. These quiet features represent intermediate algorithmic computations that do not by themselves improve the output loss. Ablation experiments demonstrate that individual quiet features are causally necessary for task performance. Our results demonstrate that substantial representational progress can remain hidden beneath an apparently flat loss curve, challenging the prevailing use of cross-entropy as a proxy for learning and motivating richer diagnostics for monitoring model training.

Leon Bergen, Timothy J. O'Donnell, Dzmitry Bahdanau

Recent research suggests that systematic generalization in natural language understanding remains a challenge for state-of-the-art neural models such as Transformers and Graph Neural Networks. To tackle this challenge, we propose Edge Transformer, a new model that combines inspiration from Transformers and rule-based symbolic AI. The first key idea in Edge Transformers is to associate vector states with every edge, that is, with every pair of input nodes -- as opposed to just every node, as it is done in the Transformer model. The second major innovation is a triangular attention mechanism that updates edge representations in a way that is inspired by unification from logic programming. We evaluate Edge Transformer on compositional generalization benchmarks in relational reasoning, semantic parsing, and dependency parsing. In all three settings, the Edge Transformer outperforms Relation-aware, Universal and classical Transformer baselines.

Leon Bergen, Dzmitry Bahdanau, Timothy J. O'Donnell

We present a model that jointly learns the denotations of words together with their groundings using a truth-conditional semantics. Our model builds on the neurosymbolic approach of Mao et al. (2019), learning to ground objects in the CLEVR dataset (Johnson et al., 2017) using a novel parallel attention mechanism. The model achieves state of the art performance on visual question answering, learning to detect and ground objects with question performance as the only training signal. We also show that the model is able to learn flexible non-canonical groundings just by adjusting answers to questions in the training set.

Charles Yu, Ryan Sie, Nico Tedeschi et al.

Neural language models learn, to varying degrees of accuracy, the grammatical properties of natural languages. In this work, we investigate whether there are systematic sources of variation in the language models' accuracy. Focusing on subject-verb agreement and reflexive anaphora, we find that certain nouns are systematically understood better than others, an effect which is robust across grammatical tasks and different language models. Surprisingly, we find that across four orders of magnitude, corpus frequency is unrelated to a noun's performance on grammatical tasks. Finally, we find that a novel noun's grammatical properties can be few-shot learned from various types of training data. The results present a paradox: there should be less variation in grammatical performance than is actually observed.

Eva Portelance, Amelia Bruno, Daniel Harasim et al.

The following technical report presents a formal approach to probabilistic minimalist grammar parameter estimation. We describe a formalization of a minimalist grammar. We then present an algorithm for the application of variational Bayesian inference to this formalization.