A Reality Check on Context Utilisation for Retrieval-Augmented Generation

• URL: http://arxiv.org/abs/2412.17031v1
• Date: Sun, 22 Dec 2024 14:16:38 GMT
• Title: A Reality Check on Context Utilisation for Retrieval-Augmented Generation
• Authors: Lovisa Hagström, Sara Vera Marjanović, Haeun Yu, Arnav Arora, Christina Lioma, Maria Maistro, Pepa Atanasova, Isabelle Augenstein,
• Abstract summary: We introduce DRUID (Dataset of Retrieved Unreliable, Insufficient and Difficult-to-understand contexts) with real-world queries and contexts manually annotated for stance. The dataset is based on the task of automated claim verification, for which automated retrieval of real-world evidence is crucial. We show that synthetic datasets exaggerate context characteristics rare in real retrieved data, which leads to inflated context utilisation results.
• Score: 44.54803681476863
• License:
• Abstract: Retrieval-augmented generation (RAG) helps address the limitations of the parametric knowledge embedded within a language model (LM). However, investigations of how LMs utilise retrieved information of varying complexity in real-world scenarios have been limited to synthetic contexts. We introduce DRUID (Dataset of Retrieved Unreliable, Insufficient and Difficult-to-understand contexts) with real-world queries and contexts manually annotated for stance. The dataset is based on the prototypical task of automated claim verification, for which automated retrieval of real-world evidence is crucial. We compare DRUID to synthetic datasets (CounterFact, ConflictQA) and find that artificial datasets often fail to represent the complex and diverse real-world context settings. We show that synthetic datasets exaggerate context characteristics rare in real retrieved data, which leads to inflated context utilisation results, as measured by our novel ACU score. Moreover, while previous work has mainly focused on singleton context characteristics to explain context utilisation, correlations between singleton context properties and ACU on DRUID are surprisingly small compared to other properties related to context source. Overall, our work underscores the need for real-world aligned context utilisation studies to represent and improve performance in real-world RAG settings.

Related papers

• TARGA: Targeted Synthetic Data Generation for Practical Reasoning over Structured Data [9.390415313514762]
  TARGA is a framework that generates high-relevance synthetic data without manual annotation. It substantially outperforms existing non-fine-tuned methods that utilize close-sourced model. It exhibits superior sample efficiency, robustness, and generalization capabilities under non-I.I.D. settings.
  arXiv  Detail & Related papers  (2024-12-27T09:16:39Z)
• Face the Facts! Evaluating RAG-based Fact-checking Pipelines in Realistic Settings [14.355271969637139]
  This work lifts several constraints of current state-of-the-art pipelines for automated fact-checking based on the Retrieval-Augmented Generation paradigm. Our goal is to benchmark, under more realistic scenarios, RAG-based methods for the generation of verdicts.
  arXiv  Detail & Related papers  (2024-12-19T18:57:11Z)
• Understanding Synthetic Context Extension via Retrieval Heads [51.8869530817334]
  We investigate fine-tuning on synthetic data for three long-context tasks that require retrieval and reasoning. We find that models trained on synthetic data fall short of the real data, but surprisingly, the mismatch can be interpreted. Our results shed light on how to interpret synthetic data fine-tuning performance and how to approach creating better data for learning real-world capabilities over long contexts.
  arXiv  Detail & Related papers  (2024-10-29T17:55:00Z)
• SFR-RAG: Towards Contextually Faithful LLMs [57.666165819196486]
  Retrieval Augmented Generation (RAG) is a paradigm that integrates external contextual information with large language models (LLMs) to enhance factual accuracy and relevance. We introduce SFR-RAG, a small LLM that is instruction-textual with an emphasis on context-grounded generation and hallucination. We also present ConBench, a new evaluation framework compiling multiple popular and diverse RAG benchmarks.
  arXiv  Detail & Related papers  (2024-09-16T01:08:18Z)
• CRoW: Benchmarking Commonsense Reasoning in Real-World Tasks [29.35269979211728]
  We present CRoW, a benchmark that evaluates the ability of models to apply commonsense reasoning in the context of six real-world NLP tasks. We use CRoW to study how NLP systems perform across different dimensions of commonsense knowledge, such as physical, temporal, and social reasoning. We find a significant performance gap when NLP systems are evaluated on CRoW compared to humans, showcasing that commonsense reasoning is far from being solved in real-world task settings.
  arXiv  Detail & Related papers  (2023-10-23T18:00:23Z)
• Zero-Shot Video Moment Retrieval from Frozen Vision-Language Models [58.17315970207874]
  We propose a zero-shot method for adapting generalisable visual-textual priors from arbitrary VLM to facilitate moment-text alignment. Experiments conducted on three VMR benchmark datasets demonstrate the notable performance advantages of our zero-shot algorithm.
  arXiv  Detail & Related papers  (2023-09-01T13:06:50Z)
• Explicit Context Integrated Recurrent Neural Network for Sensor Data Applications [0.0]
  Context Integrated RNN (CiRNN) enables integrating explicit contexts represented in the form of contextual features. Experiments show an improvement of 39% and 87% respectively, over state-of-the-art models.
  arXiv  Detail & Related papers  (2023-01-12T13:58:56Z)
• TRoVE: Transforming Road Scene Datasets into Photorealistic Virtual Environments [84.6017003787244]
  This work proposes a synthetic data generation pipeline to address the difficulties and domain-gaps present in simulated datasets. We show that using annotations and visual cues from existing datasets, we can facilitate automated multi-modal data generation.
  arXiv  Detail & Related papers  (2022-08-16T20:46:08Z)
• Learning from Context or Names? An Empirical Study on Neural Relation Extraction [112.06614505580501]
  We study the effect of two main information sources in text: textual context and entity mentions (names) We propose an entity-masked contrastive pre-training framework for relation extraction (RE) Our framework can improve the effectiveness and robustness of neural models in different RE scenarios.
  arXiv  Detail & Related papers  (2020-10-05T11:21:59Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.