Papers by Maarten de Rijke
MultiTabQA: Generating Tabular Answers for Multi-Table Question Answering (2023.acl-long)
Copied to clipboard
| Challenge: | Recent tabular question answering models only answer questions over a single table . multi-table operations often result in tabular outputs . |
| Approach: | They propose a model that answers questions over multiple tables and generalizes to generate tabular answers. |
| Outcome: | The proposed model outperforms state-of-the-art single table QA models on a multi-table QA setting. |
Learning to Ask Conversational Questions by Optimizing Levenshtein Distance (2021.acl-long)
Copied to clipboard
| Challenge: | Existing methods for estimating maximum likelihood are limited by easily learned tokens . Existing systems that generate questions based on dialogue context are limited in their ability to learn tokens. |
| Approach: | They propose a framework that optimizes the minimum Levenshtein distance through explicit editing actions. |
| Outcome: | The proposed framework outperforms state-of-the-art methods on two benchmark datasets and generalizes well on unseen data. |
WN-Salience: A Corpus of News Articles with Entity Salience Annotations (2020.lrec-1)
Copied to clipboard
| Challenge: | Existing work on entity salience does not distinguish between salient and non-salient entities. |
| Approach: | They propose a dataset to measure entity salience using WikiNews dataset . WN-Salience is built on top of Wikinews, a Wikimedia project . |
| Outcome: | The proposed dataset can be used to benchmark tasks such as entity salience detection and salient entity linking. |
The Silent Saboteur: Imperceptible Adversarial Attacks against Black-Box Retrieval-Augmented Generation Systems (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing studies have focused on corpus poisoning, but there are no studies on adversarial attacks on RAG systems. |
| Approach: | They propose a novel imperceptible retrieve-to-generate attack against RAG systems . they propose regenerative reinforcement learning framework that tracks interactions between attacker and target RAG . |
| Outcome: | The proposed framework outperforms existing attacks on factual and non-factual RAG systems with small imperceptible text perturbations. |
From Relevance to Utility: Evidence Retrieval with Feedback for Fact Verification (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Existing evidence retrieval models are based on probability ranking principle . existing models do not align with retrieval-enhanced verification frameworks . |
| Approach: | They propose a feedback-based evidence retriever that optimizes the evidence retrieval process by incorporating feedback from the claim verifier. |
| Outcome: | Empirical studies show that the proposed method is superior to baseline methods. |
A Human-machine Collaborative Framework for Evaluating Malevolence in Dialogues (2021.acl-long)
Copied to clipboard
| Challenge: | Automatic evaluation of dialogues often shows insufficient correlation with human judgements due to the diversity of responses. |
| Approach: | They propose a framework that allows automatic evaluation of dialogues with human judgements. |
| Outcome: | The proposed framework achieves 99% evaluation accuracy with half the human effort spared. |
A Comprehensive Taxonomy of Negation for NLP and Neural Retrievers (2025.findings-emnlp)
Copied to clipboard
| Challenge: | a new taxonomy of negation is proposed to improve neural information retrieval models . negation types are covered in existing datasets, allowing for faster convergence . |
| Approach: | They propose a taxonomy of negation that derives from philosophical, linguistic, and logical definitions . they also propose analyzing the performance of retrieval models on existing datasets using a logic-based classification mechanism. |
| Outcome: | The proposed taxonomy produces a balanced data distribution over negation types . it also provides a better training setup that leads to faster convergence on the NevIR dataset . |
What if Othello-Playing Language Models Could See? (2025.findings-emnlp)
Copied to clipboard
| Challenge: | a multi-modal model trained on move sequences and board images is a popular testbed for language models . |
| Approach: | They propose a multi-modal model trained jointly on move sequences and board images. |
| Outcome: | The proposed multi-modal model trains on move sequences and board images. |
Rethinking Supervised Learning and Reinforcement Learning in Task-Oriented Dialogue Systems (2020.findings-emnlp)
Copied to clipboard
| Challenge: | Dialogue policy learning for task-oriented dialogue systems has enjoyed great progress through using reinforcement learning methods. |
| Approach: | They propose a dialogue action decoder and a simulator-free adversarial learning method to improve dialogue agent performance without using reinforcement learning. |
| Outcome: | The proposed methods achieve more stable and higher performance with fewer efforts, such as the domain knowledge required to design a user simulator and the intractable parameter tuning in reinforcement learning. |
Optimized Text Embedding Models and Benchmarks for Amharic Passage Retrieval (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for multilingual and cross-lingual retrieval are lacking in low-resource, morphologically rich languages such as Amharic. |
| Approach: | They propose to train Amharic-specific dense retrieval models based on pre-trained Amharican BERT and RoBERTa backbones. |
| Outcome: | The proposed model achieves 17.6% improvement in MRR@10 and 9.86% gain in Recall@10 over the strongest multilingual baseline, Arctic Embed 2.0. |
Generalizing Few-Shot Named Entity Recognizers to Unseen Domains with Type-Related Features (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Few-shot named entity recognition methods struggle with out-of-domain (OOD) examples due to their reliance on manual labeling for the target domain. |
| Approach: | They propose a framework to enable generalization to an unseen target domain with only a few labeled examples. |
| Outcome: | The proposed framework achieves significant performance improvements on in-domain and cross-domain datasets. |
Answering Ambiguous Questions via Iterative Prompting (2023.acl-long)
Copied to clipboard
| Challenge: | Empirical studies show that AmbigPrompt achieves state-of-the-art or competitive results while using less memory and having a lower inference latency than competing approaches. |
| Approach: | They propose an answering model with a prompting model to address imperfections in open-domain question answering . Empirical studies show AmbigPrompt achieves state-of-the-art or competitive results . |
| Outcome: | The proposed framework improves on two commonly-used open benchmarks and achieves state-of-the-art or competitive results while using less memory and having a lower inference latency. |
Guided Dialogue Policy Learning without Adversarial Learning in the Loop (2020.findings-emnlp)
Copied to clipboard
Ziming Li, Sungjin Lee, Baolin Peng, Jinchao Li, Julia Kiseleva, Maarten de Rijke, Shahin Shayandeh, Jianfeng Gao
| Challenge: | Reinforcement learning methods suffer from sparse and unstable reward signals . alternating training of dialogue agent and reward model can get stuck in local optima . |
| Approach: | They propose to decompose adversarial training into two steps to improve dialogue policy learning. |
| Outcome: | The proposed method achieves remarkable task success rate using both on-policy and off-poly reinforcement learning methods. |
Evaluation of Attribution Bias in Generator-Aware Retrieval-Augmented Large Language Models (2025.findings-acl)
Copied to clipboard
| Challenge: | Prior work has focused on improving and evaluating the attribution quality of large language models (LLMs) but this may come at the expense of inducing biases in the attributed answers. |
| Approach: | They propose to evaluate attribution sensitivity and bias with respect to authorship information in large language models (LLMs) in retrieval-augmented generation pipelines. |
| Outcome: | The proposed framework can significantly improve the attribution quality of large language models (LLMs) in retrieval-augmented generation pipelines by adding authorship information to source documents. |
Controlled Retrieval-augmented Context Evaluation for Long-form RAG (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Retrieval-augmented generation (RAG) enhances large language models by incorporating context retrieved from external knowledge sources. |
| Approach: | They propose a Controlled Retrieval-aUgmented conteXt evaluation framework to directly assess retrieval-augmented contexts. |
| Outcome: | The proposed framework uses human-written summaries to control the information scope of knowledge. |