Papers by George Karypis

15 papers
Fine-Tuning Language Models on Multiple Datasets for Citation Intention Classification (2024.findings-emnlp)

Copied to clipboard

Challenge: Prior research has shown that pretrained language models (PLMs) can achieve state-of-the-art performance on CIC benchmarks.
Approach: They propose a multi-task learning framework that fine-tunes pretrained language models on a dataset of primary interest together with multiple auxiliary CIC datasets to take advantage of additional supervision signals.
Outcome: The proposed framework outperforms current state-of-the-art models on small datasets while aligning with the best-performing model on a large dataset.
Meta-learning via Language Model In-context Tuning (2022.acl-long)

Copied to clipboard

Challenge: Recent advances in large language models have reduced "task learning and prediction" to a simple sequence prediction problem.
Approach: They propose a meta-learning method that recasts task adaptation and prediction as a sequence prediction problem.
Outcome: The proposed method outperforms MAML on two classification tasks and improves on binaryClfs.
Automatic Table Union Search with Tabular Representation Learning (2023.findings-acl)

Copied to clipboard

Challenge: Existing methods to identify uniability based on column representations are insufficient to reveal latent relational features to describe column relation between pair of columns.
Approach: They propose a self-supervised table union search framework called AutoTUS to learn column relational representations in a multi-stage manner.
Outcome: The proposed framework improves on the SOTA baseline and on real-world datasets.
Exploring the Role of Task Transferability in Large-Scale Multi-Task Learning (2022.naacl-main)

Copied to clipboard

Challenge: Recent work has found that multi-task training with a large number of diverse tasks can uniformly improve downstream performance on unseen target tasks.
Approach: They aim to disentangle the effect of scale and relatedness of tasks in multi-task representation learning by increasing the number of tasks and incorporating smaller sets of related tasks.
Outcome: The proposed model improves on unseen target tasks by increasing the scale of multi-task learning to incorporate more tasks and developing similarity metrics to incorporate tasks related to the target task.
Learning to Generate Answers with Citations via Factual Consistency Models (2024.acl-long)

Copied to clipboard

Challenge: Large Language Models (LLMs) frequently hallucinate, impeding their reliability in mission-critical situations.
Approach: They propose a weakly-supervised fine-tuning method leveraging factual consistency models (FCMs) they propose to generate citations to retrieved text passages alongside LLM-produced statements .
Outcome: The proposed method improves on the ALCE few-shot citation benchmark with various instruction-tuned LLMs with an average improvement of 34.1, 15.5, and 10.5 citation F1 points.
Understanding Silent Data Corruption in LLM Training (2025.acl-long)

Copied to clipboard

Challenge: Large language models (LLMs) are a challenging task because of their large size and complexity.
Approach: They propose to isolate and analyze the impact of SDCs on LLM training by using a cloud computing platform to access unhealthy nodes swept out of production by automated fleet management.
Outcome: The proposed model training compares healthy production nodes with unhealthy nodes exhibiting SDCs at three levels: at each submodule computation, at a single optimizer step, and at . training period.
ReaRev: Adaptive Reasoning for Question Answering over Knowledge Graphs (2022.findings-emnlp)

Copied to clipboard

Challenge: Knowledge Graph Question Answering (KGQA) involves retrieving entities as answers from a Knowledge Flow using natural language queries.
Approach: They propose a method to decode a question into instructions that are dense question representations used to guide the KG traversals.
Outcome: The proposed method improves instruction decoding and execution by using a KG-aware information to update the initial instructions.
Extending Input Contexts of Language Models through Training on Segmented Sequences (2024.findings-naacl)

Copied to clipboard

Challenge: Effectively training languages models on long sequences poses many technical challenges.
Approach: They propose a method for extending positional embeddings by sub-sampling segments from long inputs while maintaining their original position.
Outcome: The proposed method extends the input con-text size of pretrained models without any changes in the model's memory and memory costs.
NameGuess: Column Name Expansion for Tabular Data (2023.emnlp-main)

Copied to clipboard

Challenge: Tabular data is used for storing and organizing information in web and enterprise applications.
Approach: They propose a task to expand column names as a natural language generation problem by conditioning on table content and column header names to improve auto-regressive models.
Outcome: The proposed task improves auto-regressive models on table content and column header names to match human performance.
CoverICL: Selective Annotation for In-Context Learning via Active Graph Coverage (2024.emnlp-main)

Copied to clipboard

Challenge: In-context learning (ICL) uses few-shot labeled examples to perform selective annotation.
Approach: They propose an algorithm that incorporates uncertainty sampling into selective annotation for ICL . CoverICL builds a nearest-neighbor graph based on the semantic similarity between candidate ICL examples .
Outcome: The proposed algorithm outperforms existing methods for low-budget active learning (AL) it is up to 2x more budget-efficient than SOTA methods for high-budge AL.
Extreme Miscalibration and the Illusion of Adversarial Robustness (2024.acl-long)

Copied to clipboard

Challenge: emergence of the Adversarial Training paradigm has shown some success in training models to be more robust to these small adversarial perturbations.
Approach: They propose to use adversarial examples to detect adversarials by miscalibrating models to mask gradients in a way that interferes with adversarial attack search methods.
Outcome: The proposed model gains are an illusion of robustness (IOR) and urge the NLP community to incorporate test-time temperature scaling into their robustness evaluations to ensure that any observed gains are genuine.
BYOKG-RAG: Multi-Strategy Graph Retrieval for Knowledge Graph Question Answering (2025.emnlp-main)

Copied to clipboard

Challenge: Existing approaches to knowledge graph question answering (KGQA) rely on Large Language Model (LLM) agents for graph traversal and retrieval.
Approach: They propose a framework that synergizes Large Language Models with specialized graph retrieval tools to enhance KGQA.
Outcome: The proposed framework outperforms the second-best graph retrieval method by 4.5% points while showing better generalization to custom KGs.
Beyond instruction-conditioning, MoTE: Mixture of Task Experts for Multi-task Embedding Models (2025.findings-acl)

Copied to clipboard

Challenge: Instruction-conditioning has become the dominant approach for embedding specialization, but its direct application to low-capacity models imposes representational constraints that limit the performance gains derived from specialization.
Approach: They propose a mixture of task experts transformer block which leverages task-specialized parameters trained with Task-Aware Contrastive Learning to enhance the model’s ability to generate specialized embeddings.
Outcome: The proposed model achieves 64% higher performance gains in retrieval datasets (+3.27 +5.21) and 43% higher performance gain across all datasets (+1.81 2.60).
Evaluating Scholarly Impact: Towards Content-Aware Bibliometrics (2021.emnlp-main)

Copied to clipboard

Challenge: Scientific, engineering, and technological (SET) innovations drive many positive advances in our modern economy, society, and life.
Approach: They propose a new metric that uses the content of the paper as a source of distant-supervision to quantify how much the cited-node informs the citing-n node.
Outcome: The proposed method achieves up to 103% improvement over the second-best method.
GNN-RAG: Graph Neural Retrieval for Efficient Large Language Model Reasoning on Knowledge Graphs (2025.findings-acl)

Copied to clipboard

Challenge: Existing approaches to retrieval-augmented generation (RAG) rely on costly LLM calls to generate relation paths or traverse the KG.
Approach: They propose a framework that uses lightweight Graph Neural Networks to enhance retrieval.
Outcome: The proposed framework outperforms existing methods on multi-hop and multi-entity questions.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations