Papers by Max Glockner
Missci: Reconstructing Fallacies in Misrepresented Science (2024.acl-long)
Copied to clipboard
| Challenge: | False or misleading narratives spread rapidly on social networks, posing challenges for non-experts in discerning credible information. |
| Approach: | They propose a model for fallacious reasoning that focuses on implicit fallacies between relevant content and the inaccurate claim and requires models to verbalize the fallacious thinking in addition to classifying it. |
| Outcome: | The proposed model focuses on implicit fallacies between relevant content and the inaccurate claim and requires models to verbalize the fallacious reasoning in addition to classifying it. |
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. |
Why do you think that? Exploring Faithful Sentence-Level Rationales Without Supervision (2020.findings-emnlp)
Copied to clipboard
| Challenge: | Large pre-trained language models, such as BERT or RoBERTa, gain impressive results on a large variety of NLP tasks, including reasoning and inference. |
| Approach: | They propose a differentiable training framework to create models which output faithful rationales on a sentence level, by solely applying supervision on the target task. |
| Outcome: | The proposed model outperforms pipeline approaches and non-differentiable models on three different datasets while exceeding pipeline counterparts. |
AdapterDrop: On the Efficiency of Adapters in Transformers (2021.emnlp-main)
Copied to clipboard
Andreas Rücklé, Gregor Geigle, Max Glockner, Tilman Beck, Jonas Pfeiffer, Nils Reimers, Iryna Gurevych
| Challenge: | Recent approaches to transformer models are expensive to fine-tune, slow for inference, and have large storage requirements. |
| Approach: | They propose a method to remove adapters from transformer layers during training and inference . they show that AdapterDrop can dynamically reduce computational overhead . |
| Outcome: | The proposed approach reduces computational overhead while maintaining performance over multiple tasks with minimal loss of performance. |
Missing Counter-Evidence Renders NLP Fact-Checking Unrealistic for Misinformation (2022.emnlp-main)
Copied to clipboard
| Challenge: | Existing NLP task definitions for fact-checking cannot refute misinformation as professional fact- checkers do for the majority of claims. |
| Approach: | They compare NLP-based fact-checking with professional fact- checkers . they find that evidence must be sufficient to refute the claim and not leaked . |
| Outcome: | The proposed models fail to meet the criteria for realistic fact-checking . they also fail to satisfy the criteria of leaked evidence . |
Breaking NLI Systems with Sentences that Require Simple Lexical Inferences (P18-2)
Copied to clipboard
| Challenge: | a new test set shows the deficiency of state-of-the-art models in inferences that require lexical and world knowledge. |
| Approach: | They create a new NLI test set that shows the deficiency of state-of-the-art models in inferences that require lexical and world knowledge. |
| Outcome: | The new examples are simpler than the SNLI test set, but the state-of-the-art systems perform poorly on it. |
Grounding Fallacies Misrepresenting Scientific Publications in Evidence (2025.naacl-long)
Copied to clipboard
| Challenge: | Current fact-checking models struggle to use misrepresented scientific passages to refute misinformation. |
| Approach: | They propose an extension of the fallacy detection dataset Missci to detect and highlight such fallacies by grounding applied fallacias in real-world passages from misrepresented studies. |
| Outcome: | The proposed model can detect and highlight misrepresented publications and verbalize them to refute them. |