arXiv subjects

Cornelia Caragea

Publications and source records attributed to Cornelia Caragea.

At least 19 recordsLinked to original sources

arXiv2026

Scaling Performance and Low-Resource Annotation with Many-Shot In-Context Learning for Named Entity Recognition

In-context learning (ICL) with large language models (LLMs) has emerged as a powerful alternative to fine-tuning for Named Entity Recognition (NER), achieving strong performance with minimal annotation and no additional training. However, prior work has shown that despite their adaptability, LLMs still lag behind fully supervised models such as fine-tuned BERT in structured tasks like NER. While existing studies on ICL for NER have mainly explored few-shot settings, the potential of scaling to hundreds of demonstrations has not been thoroughly investigated. To address this gap, we conduct a comprehensive investigation of many-shot ICL for NER and further explore its effectiveness in annotating and refining data for low-resource NER tasks. Specifically, we evaluate various LLMs across multiple domains using hundreds of ICL examples and then assess the feasibility of using many-shot ICL as a data annotation framework. Our experiments demonstrate that: (1) scaling to hundreds of in-context examples enables LLMs to match or even surpass the performance of fully supervised BERT models; and (2) using about one hundred human-labeled examples as demonstrations, many-shot in-context annotation can generate high-quality labeled data, leading to approximately 10% absolute F1 improvement over existing state-of-the-art approaches when used to fine-tune BERT on low-resource NER.

cs.CL↗

arXiv2026

CaliDist: Calibrating Large Language Models via Behavioral Robustness to Distraction

Existing calibration methods for Large Language Models (LLMs) often overlook a critical dimension of trustworthiness: a model's behavioral robustness to irrelevant or misleading information. In this paper, we argue that a model's true confidence should reflect its stability under cognitive pressure. We introduce CaliDist, a novel post-hoc calibration approach that directly measures and penalizes a model's susceptibility to distraction. CaliDist quantifies how an LLM's predictions and uncertainty change when its input prompt is perturbed with semantic distractors. This stability (or lack thereof) signal is then used to adaptively scale the model's initial confidence score. Our extensive experiments on seven Natural Language Understanding classification benchmarks using six distinct LLMs show that CaliDist consistently achieves lower Expected Calibration Error (ECE) and Brier Score compared with strong baselines. Remarkably, our method reduces the ECE from 23% to 7% on average--a relative improvement of 70%--demonstrating that behavioral stability is a powerful signal for calibration. We make our code and datasets available at github.com/anas-jawad/CaliDist.

cs.LG↗

arXiv2026

LLM-guided Semi-Supervised Approaches for Social Media Crisis Data Classification

Semi-supervised learning approaches have been investigated as a means to enhance the analysis of social media data in disaster management contexts. In this work, we present the first empirical evaluation of large language model (LLM) guided semi-supervised learning for crisis related tweet classification. We compare two recent LLM assisted semi-supervised methods, VerifyMatch and LLM guided Co-Training ( LG-CoTrain), against established semi-supervised baselines. Our results show that LG-CoTrain significantly outperforms classical semi-supervised approaches in low resource settings with 5, 10 and 25 labeled examples per class, achieving the highest averaged Macro F1 across events. VerifyMatch achieves competitive performance while also demonstrating strong calibration properties. As the number of labeled examples increases, the performance gap narrows and Self Training emerges as a strong baseline. We further observe that compact semi-supervised models can, in some cases, outperform very large LLMs operating in zero-shot settings. This finding highlights the potential of transferring knowledge from LLMs into smaller and more deployable models through LLM guided semi-supervised learning, offering a practical pathway for real world disaster response applications. Our project repository on Github is here.

cs.AI↗

arXiv2026

BLooP: Zero-Shot Abstractive Summarization using Large Language Models with Bigram Lookahead Promotion

Abstractive summarization requires models to generate summaries that convey information in the source document. While large language models can generate summaries without fine-tuning, they often miss key details and include extraneous information. We propose BLooP (Bigram Lookahead Promotion), a simple training-free decoding intervention that encourages large language models (LLMs) to generate tokens that form bigrams from the source document. BLooP operates through a hash table lookup at each decoding step, requiring no training, fine-tuning, or model modification. We demonstrate improvements in ROUGE and BARTScore for Llama-3.1-8B-Instruct, Mistral-Nemo-Instruct-2407, and Gemma-2-9b-it on CNN/DM, CCSum, Multi-News, and SciTLDR. Human evaluation shows that BLooP significantly improves faithfulness without reducing readability. We make the code available at https://github.com/varuniyer/BLooP

cs.CL↗

arXiv2025

The Shifting Landscape of Vaccine Discourse: Insights From a Decade of Pre- to Post-COVID-19 Vaccine Posts on Social Media

In this work, we study English-language vaccine discourse in social media posts, specifically posts on X (formerly Twitter), in seven years before the COVID-19 outbreak (2013 to 2019) and three years after the outbreak was first reported (2020 to 2022). Drawing on theories from social cognition and the stereotype content model in Social Psychology, we analyze how English speakers talk about vaccines on social media to understand the evolving narrative around vaccines in social media posts. To do that, we first introduce a novel dataset comprising 18.7 million curated posts on vaccine discourse from 2013 to 2022. This extensive collection-filtered down from an initial 129 million posts through rigorous preprocessing-captures both pre-COVID and COVID-19 periods, offering valuable insights into the evolution of English-speaking X users' perceptions related to vaccines. Our analysis shows that the COVID-19 pandemic led to complex shifts in X users' sentiment and discourse around vaccines. We observe that negative emotion word usage decreased during the pandemic, with notable rises in usage of surprise, and trust related emotion words. Furthermore, vaccine-related language tended to use more warmth-focused words associated with trustworthiness, along with positive, competence-focused words during the early days of the pandemic, with a marked rise in negative word usage towards the end of the pandemic, possibly reflecting a growing vaccine hesitancy and skepticism.

cs.SI↗

arXiv2025

CalibrateMix: Guided-Mixup Calibration of Image Semi-Supervised Models

Semi-supervised learning (SSL) has demonstrated high performance in image classification tasks by effectively utilizing both labeled and unlabeled data. However, existing SSL methods often suffer from poor calibration, with models yielding overconfident predictions that misrepresent actual prediction likelihoods. Recently, neural networks trained with {\tt mixup} that linearly interpolates random examples from the training set have shown better calibration in supervised settings. However, calibration of neural models remains under-explored in semi-supervised settings. Although effective in supervised model calibration, random mixup of pseudolabels in SSL presents challenges due to the overconfidence and unreliability of pseudolabels. In this work, we introduce CalibrateMix, a targeted mixup-based approach that aims to improve the calibration of SSL models while maintaining or even improving their classification accuracy. Our method leverages training dynamics of labeled and unlabeled samples to identify ``easy-to-learn'' and ``hard-to-learn'' samples, which in turn are utilized in a targeted mixup of easy and hard samples. Experimental results across several benchmark image datasets show that our method achieves lower expected calibration error (ECE) and superior accuracy compared to existing SSL approaches.

cs.CV↗

arXiv2025

Evaluating Large Language Models for Stance Detection on Financial Targets from SEC Filing Reports and Earnings Call Transcripts

Financial narratives from U.S. Securities and Exchange Commission (SEC) filing reports and quarterly earnings call transcripts (ECTs) are very important for investors, auditors, and regulators. However, their length, financial jargon, and nuanced language make fine-grained analysis difficult. Prior sentiment analysis in the financial domain required a large, expensive labeled dataset, making the sentence-level stance towards specific financial targets challenging. In this work, we introduce a sentence-level corpus for stance detection focused on three core financial metrics: debt, earnings per share (EPS), and sales. The sentences were extracted from Form 10-K annual reports and ECTs, and labeled for stance (positive, negative, neutral) using the advanced ChatGPT-o3-pro model under rigorous human validation. Using this corpus, we conduct a systematic evaluation of modern large language models (LLMs) using zero-shot, few-shot, and Chain-of-Thought (CoT) prompting strategies. Our results show that few-shot with CoT prompting performs best compared to supervised baselines, and LLMs' performance varies across the SEC and ECT datasets. Our findings highlight the practical viability of leveraging LLMs for target-specific stance in the financial domain without requiring extensive labeled data.

cs.CL↗

arXiv2025

MADIAVE: Multi-Agent Debate for Implicit Attribute Value Extraction

Implicit Attribute Value Extraction (AVE) is essential for accurately representing products in e-commerce, as it infers latent attributes from multimodal data. Despite advances in multimodal large language models (MLLMs), implicit AVE remains challenging due to the complexity of multidimensional data and gaps in vision-text understanding. In this work, we introduce MADIAVE, a multi-agent debate framework that employs multiple MLLM agents to iteratively refine inferences. Through a series of debate rounds, agents verify and update each other's responses, thereby improving inference performance and robustness. Experiments on the ImplicitAVE dataset demonstrate that even a few rounds of debate significantly boost accuracy, especially for attributes with initially low performance. We systematically evaluate various debate configurations, including identical or different MLLM agents, and analyze how debate rounds affect convergence dynamics. Our findings highlight the potential of multi-agent debate strategies to address the limitations of single-agent approaches and offer a scalable solution for implicit AVE in multimodal e-commerce.

cs.CL↗

arXiv2025

LLM-Guided Co-Training for Text Classification

In this paper, we introduce a novel weighted co-training approach that is guided by Large Language Models (LLMs). Namely, in our co-training approach, we use LLM labels on unlabeled data as target labels and co-train two encoder-only based networks that train each other over multiple iterations: first, all samples are forwarded through each network and historical estimates of each network's confidence in the LLM label are recorded; second, a dynamic importance weight is derived for each sample according to each network's belief in the quality of the LLM label for that sample; finally, the two networks exchange importance weights with each other -- each network back-propagates all samples weighted with the importance weights coming from its peer network and updates its own parameters. By strategically utilizing LLM-generated guidance, our approach significantly outperforms conventional SSL methods, particularly in settings with abundant unlabeled data. Empirical results show that it achieves state-of-the-art performance on 4 out of 5 benchmark datasets and ranks first among 14 compared methods according to the Friedman test. Our results highlight a new direction in semi-supervised learning -- where LLMs serve as knowledge amplifiers, enabling backbone co-training models to achieve state-of-the-art performance efficiently.

cs.LG↗

arXiv2025

Towards AI-Assisted Research Writing: Benchmarking LLMs for AI/ML Introduction Generation

As researchers increasingly adopt LLMs as writing assistants, generating high-quality research paper introductions remains both challenging and essential. We introduce Scientific Introduction Generation (SciIG), a task that evaluates LLMs' ability to produce coherent introductions from titles, abstracts, and related works. Curating new datasets from NAACL 2025 and ICLR 2025 papers, we assess five state-of-the-art models, including both open-source (DeepSeek-v3, Gemma-3-12B, LLaMA 4-Maverick, MistralAI Small 3.1) and closed-source GPT-4o systems, across multiple dimensions: lexical overlap, semantic similarity, content coverage, faithfulness, consistency, citation correctness, and narrative quality. Our comprehensive framework combines automated metrics with LLM-as-a-judge evaluations. Results demonstrate LLaMA-4 Maverick's superior performance on most metrics, particularly in semantic similarity and faithfulness. Moreover, three-shot prompting consistently outperforms fewer-shot approaches. These findings provide practical insights into developing effective research writing assistants and set realistic expectations for LLM-assisted academic writing. To foster re- producibility and future research, we publicly release all code and datasets.

cs.CL↗

arXiv2025

MultiMatch: Multihead Consistency Regularization Matching for Semi-Supervised Text Classification

We introduce MultiMatch, a novel semi-supervised learning (SSL) algorithm combining the paradigms of co-training and consistency regularization with pseudo-labeling. At its core, MultiMatch features a pseudo-label weighting module designed for selecting and filtering pseudo-labels based on head agreement and model confidence, and weighting them according to the perceived classification difficulty. This novel module enhances and unifies three existing techniques -- heads agreement from Multihead Co-training, self-adaptive thresholds from FreeMatch, and Average Pseudo-Margins from MarginMatch -- resulting in a holistic approach that improves robustness and performance in SSL settings. Experimental results on benchmark datasets highlight the superior performance of MultiMatch, i.e., MultiMatch achieves state-of-the-art results on 8 out of 10 setups from 5 natural language processing datasets and ranks first according to the Friedman test among 21 methods. Furthermore, MultiMatch demonstrates exceptional robustness in highly imbalanced settings, outperforming the second-best approach by 3.26%, a critical advantage for real-world text classification tasks. Our code is available on GitHub.

cs.CL↗

arXiv2025

A MISMATCHED Benchmark for Scientific Natural Language Inference

Scientific Natural Language Inference (NLI) is the task of predicting the semantic relation between a pair of sentences extracted from research articles. Existing datasets for this task are derived from various computer science (CS) domains, whereas non-CS domains are completely ignored. In this paper, we introduce a novel evaluation benchmark for scientific NLI, called MISMATCHED. The new MISMATCHED benchmark covers three non-CS domains-PSYCHOLOGY, ENGINEERING, and PUBLIC HEALTH, and contains 2,700 human annotated sentence pairs. We establish strong baselines on MISMATCHED using both Pre-trained Small Language Models (SLMs) and Large Language Models (LLMs). Our best performing baseline shows a Macro F1 of only 78.17% illustrating the substantial headroom for future improvements. In addition to introducing the MISMATCHED benchmark, we show that incorporating sentence pairs having an implicit scientific NLI relation between them in model training improves their performance on scientific NLI. We make our dataset and code publicly available on GitHub.

cs.CL↗

arXiv2025

DynClean: Training Dynamics-based Label Cleaning for Distantly-Supervised Named Entity Recognition

Distantly Supervised Named Entity Recognition (DS-NER) has attracted attention due to its scalability and ability to automatically generate labeled data. However, distant annotation introduces many mislabeled instances, limiting its performance. Most of the existing work attempt to solve this problem by developing intricate models to learn from the noisy labels. An alternative approach is to attempt to clean the labeled data, thus increasing the quality of distant labels. This approach has received little attention for NER. In this paper, we propose a training dynamics-based label cleaning approach, which leverages the behavior of a model as training progresses to characterize the distantly annotated samples. We also introduce an automatic threshold estimation strategy to locate the errors in distant labels. Extensive experimental results demonstrate that: (1) models trained on our cleaned DS-NER datasets, which were refined by directly removing identified erroneous annotations, achieve significant improvements in F1-score, ranging from 3.18% to 8.95%; and (2) our method outperforms numerous advanced DS-NER approaches across four datasets.

cs.CL↗

arXiv2025

Zero-Shot Keyphrase Generation: Investigating Specialized Instructions and Multi-Sample Aggregation on Large Language Models

Keyphrases are the essential topical phrases that summarize a document. Keyphrase generation is a long-standing NLP task for automatically generating keyphrases for a given document. While the task has been comprehensively explored in the past via various models, only a few works perform some preliminary analysis of Large Language Models (LLMs) for the task. Given the impact of LLMs in the field of NLP, it is important to conduct a more thorough examination of their potential for keyphrase generation. In this paper, we attempt to meet this demand with our research agenda. Specifically, we focus on the zero-shot capabilities of open-source instruction-tuned LLMs (Phi-3, Llama-3) and the closed-source GPT-4o for this task. We systematically investigate the effect of providing task-relevant specialized instructions in the prompt. Moreover, we design task-specific counterparts to self-consistency-style strategies for LLMs and show significant benefits from our proposals over the baselines.

cs.CL↗

arXiv2025

Active Few-Shot Learning for Text Classification

The rise of Large Language Models (LLMs) has boosted the use of Few-Shot Learning (FSL) methods in natural language processing, achieving acceptable performance even when working with limited training data. The goal of FSL is to effectively utilize a small number of annotated samples in the learning process. However, the performance of FSL suffers when unsuitable support samples are chosen. This problem arises due to the heavy reliance on a limited number of support samples, which hampers consistent performance improvement even when more support samples are added. To address this challenge, we propose an active learning-based instance selection mechanism that identifies effective support instances from the unlabeled pool and can work with different LLMs. Our experiments on five tasks show that our method frequently improves the performance of FSL. We make our implementation available on GitHub.

cs.CL↗

arXiv2025

Investigating Recurrent Transformers with Dynamic Halt

In this paper, we comprehensively study the inductive biases of two major approaches to augmenting Transformers with a recurrent mechanism: (1) the approach of incorporating a depth-wise recurrence similar to Universal Transformers; and (2) the approach of incorporating a chunk-wise temporal recurrence like Temporal Latent Bottleneck. Furthermore, we propose and investigate novel ways to extend and combine the above methods - for example, we propose a global mean-based dynamic halting mechanism for Universal Transformers and an augmentation of Temporal Latent Bottleneck with elements from Universal Transformer. We compare the models and probe their inductive biases in several diagnostic tasks, such as Long Range Arena (LRA), flip-flop language modeling, ListOps, and Logical Inference. The code is released in: https://github.com/JRC1995/InvestigatingRecurrentTransformers/tree/main

cs.LG↗

arXiv2025

Zero-Shot Verification-guided Chain of Thoughts

Previous works have demonstrated the effectiveness of Chain-of-Thought (COT) prompts and verifiers in guiding Large Language Models (LLMs) through the space of reasoning. However, most such studies either use a fine-tuned verifier or rely on manually handcrafted few-shot examples. In contrast, in this paper, we focus on LLM-based self-verification of self-generated reasoning steps via COT prompts in a completely zero-shot regime. To explore this setting, we design a new zero-shot prompt, which we call COT STEP, to aid zero-shot decomposition of reasoning steps and design two new zero-shot prompts for LLM-based verifiers. We evaluate the verifiers' ability to classify the correctness of reasoning chains and explore different ways to use verifier scores in guiding reasoning for various mathematical and commonsense reasoning tasks with different LLMs.

cs.CL↗

arXiv2024

SciER: An Entity and Relation Extraction Dataset for Datasets, Methods, and Tasks in Scientific Documents

Scientific information extraction (SciIE) is critical for converting unstructured knowledge from scholarly articles into structured data (entities and relations). Several datasets have been proposed for training and validating SciIE models. However, due to the high complexity and cost of annotating scientific texts, those datasets restrict their annotations to specific parts of paper, such as abstracts, resulting in the loss of diverse entity mentions and relations in context. In this paper, we release a new entity and relation extraction dataset for entities related to datasets, methods, and tasks in scientific articles. Our dataset contains 106 manually annotated full-text scientific publications with over 24k entities and 12k relations. To capture the intricate use and interactions among entities in full texts, our dataset contains a fine-grained tag set for relations. Additionally, we provide an out-of-distribution test set to offer a more realistic evaluation. We conduct comprehensive experiments, including state-of-the-art supervised models and our proposed LLM-based baselines, and highlight the challenges presented by our dataset, encouraging the development of innovative models to further the field of SciIE.

cs.CL↗