Papers by Markus Dreyer
Multi-Task Networks with Universe, Group, and Task Feature Learning (P19-1)
Copied to clipboard
| Challenge: | In multi-task learning, multiple related tasks are learned together. |
| Approach: | They propose methods that take advantage of natural groupings of related tasks . they propose parallel and serial architectures that can learn different feature spaces . |
| Outcome: | The proposed methods improve performance on natural language understanding (NLU) tasks. |
REFINESUMM: Self-Refining MLLM for Generating a Multimodal Summarization Dataset (2024.acl-long)
Copied to clipboard
| Challenge: | generating accurate and faithful multimodal summaries is challenging due to lack of appropriate multimodal datasets . large language models excel at synthesizing key information from diverse sources, but lack of adequate multimodal data sets for fine-tuning . |
| Approach: | They propose a dataset specifically designed for image-text multimodal summarization . they generate summaries from Wikipedia sections and corresponding images and evaluate them . |
| Outcome: | The proposed dataset improves summary quality by training a critic model on human annotations and using its predictions to remove low-quality summaries. |
Efficiently Summarizing Text and Graph Encodings of Multi-Document Clusters (2021.naacl-main)
Copied to clipboard
| Challenge: | Abstractive multi-document summarization (MDS) is a task that has seen advances with the introduction of large-scale datasets and powerful Transformer-based models. |
| Approach: | They propose an efficient graph-enhanced approach to multi-document summarization with an encoder-decoder Transformer model. |
| Outcome: | The proposed model scales to large input documents and improves on a multi-document dataset. |
Background Summarization of Event Timelines (2023.emnlp-main)
Copied to clipboard
| Challenge: | Generating concise summaries of news events is a challenging task for newcomers to a news story. |
| Approach: | They propose a task of background news summarization that complements each timeline update with a background summary of relevant preceding events. |
| Outcome: | The proposed system performs well on a question-answering-based evaluation metric, Background Utility Score (BUS). |
NeoQA: Evidence-based Question Answering with Generated News Events (2025.findings-acl)
Copied to clipboard
| Challenge: | Evaluating Retrieval-Augmented Generation (RAG) in large language models is challenging because benchmarks can quickly become stale. |
| Approach: | They propose a benchmark to evaluate Retrieval-Augmented Generation (RAG) in large language models (LLMs) using timelines and knowledge bases of fictional news events and entities to prevent LLMs from leveraging pretraining knowledge. |
| Outcome: | The proposed benchmark prevents LLMs from leveraging pretraining knowledge and ensures that no prior evidence exists in their training data. |
FactGraph: Evaluating Factuality in Summarization with Semantic Graph Representations (2022.naacl-main)
Copied to clipboard
| Challenge: | Recent studies show that abstractive summarization approaches generate summaries that are not factually consistent with the source document. |
| Approach: | They propose a method that decomposes the document and summary into structured meaning representations (MRs) MRs describe core semantic concepts and their relations, aggregating the main content in both document and summary in a canonical form . |
| Outcome: | The proposed method outperforms existing methods on benchmarks for factuality evaluation. |
CCSum: A Large-Scale and High-Quality Dataset for Abstractive News Summarization (2024.naacl-long)
Copied to clipboard
| Challenge: | Existing datasets for supervised news summarization contain considerable amount of noise and expensive training data. |
| Approach: | They propose a large-scale and high-quality dataset for supervised abstractive news summarization containing 1.3 million training samples. |
| Outcome: | The proposed dataset is more factual and informative than established summarization datasets. |
RefusalBench: Generative Evaluation of Selective Refusal in Grounded Language Models (2026.eacl-long)
Copied to clipboard
| Challenge: | Language models fail to selectively refuse to answer based on flawed context, study finds . current benchmarks fail to evaluate complex capabilities like selective refusal . |
| Approach: | They propose a framework that generates diagnostic test cases through controlled linguistic perturbation. |
| Outcome: | The proposed framework employs 176 perturbation strategies across six categories of uncertainty and three intensity levels. |
Evaluating the Tradeoff Between Abstractiveness and Factuality in Abstractive Summarization (2023.findings-eacl)
Copied to clipboard
| Challenge: | Abstractive summarization models generate fluent and well-formed output but lack semantic faithfulness, or factuality, with respect to the input documents. |
| Approach: | They propose new factuality metrics that adjust for the degree of abstractiveness . they propose to visualize the rates of change in factual as we gradually increase abstractiveity . |
| Outcome: | The proposed models generate fluent and well-formed summaries but lack semantic faithfulness, or factuality, with respect to the input documents. |
Faithfulness-Aware Decoding Strategies for Abstractive Summarization (2023.eacl-main)
Copied to clipboard
| Challenge: | Existing studies on faithfulness of abstractive summarization have focused on decoding strategies. |
| Approach: | They propose two faithfulness-aware generation methods to further improve faithfulness . they propose to use a distillation approach to generate faithful summaries with greedy decoding . |
| Outcome: | The proposed methods improve faithfulness across two datasets as evaluated by automatic faithfulness metrics and human evaluation. |
DeepFact: Co-Evolving Benchmarks and Agents for Deep Research Factuality (2026.acl-long)
Copied to clipboard
Yukun Huang, Leonardo F. R. Ribeiro, Momchil Hardalov, Bhuwan Dhingra, Markus Dreyer, Venkatesh Saligrama
| Challenge: | Existing fact-checkers usually target general-domain atomic claims . citation-grounded fact- checking ignores claims without explicit citations . |
| Approach: | They propose to use a benchmark to test whether claim-level factuality is transferable . they instantiate **Audit-then-Score** as a versioned DRR factualism benchmark . |
| Outcome: | The proposed benchmark outperforms the best prior deep-research and traditional fact-checkers by 14.3 and 24.9 points. |
Unified Embeddings for Multimodal Retrieval via Frozen LLMs (2024.findings-eacl)
Copied to clipboard
| Challenge: | Unified Embeddings for Multimodal Retrieval (UniMuR) is a simple but effective approach that embeds multimodal inputs and retrieves visual and textual outputs via frozen Large Language Models (LLMs). |
| Approach: | They propose a method that embeds multimodal inputs and retrieves visual and textual outputs via frozen Large Language Models (LLMs). |
| Outcome: | The proposed method significantly reduces LLM’s modality bias towards generating text-only outputs and achieves strong image/text retrieval ability. |
Enhancing Multi-Document Summarization with Cross-Document Graph-based Information Extraction (2023.eacl-main)
Copied to clipboard
| Challenge: | Information extraction (IE) and summarization (summarization) are closely related, but both aims to abstract the most salient information into a generated text summary. |
| Approach: | They propose to use structured IE graphs to enhance the abstractive summarization task by using cross-document IE output to incorporate an alignment loss between IE nodes and their text spans to reduce inconsistencies. |
| Outcome: | The proposed model can generate summaries that are more factual while not losing abstractiveness. |
Efficient Few-Shot Fine-Tuning for Opinion Summarization (2022.findings-naacl)
Copied to clipboard
| Challenge: | Abstractive summarization models are typically pre-trained on large amounts of generic texts . large annotated datasets of reviews paired with reference summaries are not available . |
| Approach: | They propose a few-shot method which uses adapters to store in-domain knowledge . they pre-train adapters on unannotated customer reviews and fine-tune them on annotated datasets . |
| Outcome: | The proposed method can store in-domain knowledge and improves on large annotated reviews . it improves coherence and redundancies on the Amazon and Yelp datasets . |
Generating Summaries with Controllable Readability Levels (2023.emnlp-main)
Copied to clipboard
| Challenge: | Current text generation approaches focus on a specific readability level, resulting in texts that are not customized to readers’ proficiency levels. |
| Approach: | They propose to generate summaries with fine-grained control over their readability by using instruction-based readability control, reinforcement learning and lookahead to estimate readability of upcoming decoding steps. |
| Outcome: | The generated summaries with different readability levels were compared with previous methods that focus on a specific readability level (e.g., lay summarization) and a lookahead approach significantly improved readability control on news summarizing. |