Can Generative Pre-trained Language Models Serve As Knowledge Bases for Closed-book QA? (2021.acl-long)
Copied to clipboard
| Challenge: | Existing work is limited in using small benchmarks with high test-train overlaps. |
| Approach: | They construct a dataset of closed-book QA using SQuAD and investigate the performance of BART. |
| Outcome: | Experiments show that pre-trained language models can achieve high performance on closed-book QA tasks. |
Similar Papers
Augmenting Pre-trained Language Models with QA-Memory for Open-Domain Question Answering (2023.eacl-main)
Copied to clipboard
| Challenge: | Existing methods for open-domain question-answering use an open book approach . a recent alternative is to retrieve from a collection of previously-generated question-annwer pairs . |
| Approach: | They propose a new QA system that augments a text-to-text model with a large memory of question-answer pairs and a task for the latent step of question retrieval. |
| Outcome: | The proposed system outperforms closed-book QA and can answer multi-hop questions. |
Language Models as Knowledge Bases? (D19-1)
Copied to clipboard
Fabio Petroni, Tim Rocktäschel, Sebastian Riedel, Patrick Lewis, Anton Bakhtin, Yuxiang Wu, Alexander Miller
| Challenge: | Recent advances in pretraining language models on large textual corpora led to a surge of improvements for downstream NLP tasks. |
| Approach: | They present a method for pretraining language models on large textual corpora . they find that they can store relational knowledge and answer queries structured as "fill-in-the-blank" queries. |
| Outcome: | The proposed language models can recall factual knowledge without fine-tuning without fine tuning . the proposed models can answer queries structured as "fill-in-the-blank" cloze statements . |
How Much Knowledge Can You Pack Into the Parameters of a Language Model? (2020.emnlp-main)
Copied to clipboard
| Challenge: | In this paper, we show that large neural language models trained on unstructured text can attain competitive results on open-domain question answering benchmarks without access to external knowledge. |
| Approach: | They propose to fine-tune pre-trained neural language models to answer questions without external knowledge . they show that this approach scales with model size and performs competitively . |
| Outcome: | The proposed approach scales with model size and performs competitively with open-domain systems that explicitly retrieve answers from an external knowledge source when answering questions. |
Can NLI Models Verify QA Systems’ Predictions? (2021.findings-emnlp)
Copied to clipboard
| Challenge: | Recent question answering systems perform well on benchmark datasets, but are not always well-calibrated to spot spurious answers under distribution shifts. |
| Approach: | They propose to use natural language inference to verify whether answers are correct . they leverage large pre-trained models and recent prior datasets to construct powerful question conversion and decontextualization modules. |
| Outcome: | The proposed approach improves the confidence estimation of a QA model across different domains, evaluated in a selective QA setting. |
DIVKNOWQA: Assessing the Reasoning Ability of LLMs via Open-Domain Question Answering over Knowledge Base and Text (2024.findings-naacl)
Copied to clipboard
| Challenge: | Retrievalaugmented LLMs have been used to ground LLM in external knowledge . a gap exists in the current landscape regarding the effectiveness of grounding LLM on heterogeneous knowledge sources. |
| Approach: | They propose a model that uses symbolic language to generate symbolic queries . they use a dataset that is generated using predefined reasoning chains and human annotation . |
| Outcome: | The proposed model outperforms previous approaches by a significant margin in QA tasks over text. |
Perhaps PTLMs Should Go to School – A Task to Assess Open Book and Closed Book QA (2021.emnlp-main)
Copied to clipboard
| Challenge: | Taking the exam closed book, but having read the textbook, yields at best minor improvement (56%), suggesting that the PTLM may not have “understood” the textbook (or perhaps misundersttoo the questions). |
| Approach: | They propose to use pre-trained language models to answer questions from introductory college textbooks and hundreds of true/false statements based on review questions written by the authors. |
| Outcome: | The proposed task includes two college-level introductory texts in the social sciences (American Government 2e) and humanities (U.S. History). |
Can Pretrained Language Models (Yet) Reason Deductively? (2023.eacl-main)
Copied to clipboard
| Challenge: | Acquiring factual knowledge with Pretrained Language Models (PLMs) has attracted increasing attention, showing promising performance in many knowledge-intensive tasks. |
| Approach: | They conduct a comprehensive evaluation of the learnable deductive reasoning capability of pretrained language models and compare their performance against simple adversarial surface form edits. |
| Outcome: | The models are able to generalise learned logic rules and perform inconsistently against simple adversarial surface form edits, but catastrophically forget the previously learnt knowledge. |
Context Generation Improves Open Domain Question Answering (2023.findings-eacl)
Copied to clipboard
Dan Su, Mostofa Patwary, Shrimai Prabhumoye, Peng Xu, Ryan Prenger, Mohammad Shoeybi, Pascale Fung, Anima Anandkumar, Bryan Catanzaro
| Challenge: | Existing closed-book question answering methods do not fully exploit the parameterized knowledge. |
| Approach: | They propose a closed-book QA framework which uses a coarse-to-fine approach to extract the relevant knowledge and answer a question. |
| Outcome: | The proposed method outperforms open-book QA methods on three QA benchmarks. |
What do Models Learn from Question Answering Datasets? (2020.emnlp-main)
Copied to clipboard
| Challenge: | Existing models have outperformed humans on question answering datasets, but they have yet to outperform humans on the task of question answering itself. |
| Approach: | They evaluate BERT-based question answering models on their generalizability to out-of-domain examples, responses to missing or incorrect data, and ability to handle question variations. |
| Outcome: | The proposed models outperform human baselines on the widely-used SQuAD 1.1 and SQu AD 2.0 datasets. |
Generalizing Question Answering System with Pre-trained Language Model Fine-tuning (D19-58)
Copied to clipboard
| Challenge: | Existing methods focus on improving in-domain performance, leaving open the question of how they can generalize to out-of-domain and unseen RC tasks. |
| Approach: | They propose a multi-task learning framework that learns the shared representation across different tasks and builds on a large pre-trained language model and fine-tuned on multiple RC datasets. |
| Outcome: | The proposed framework improves the BERT-Large baseline by 8.39 and 7.22 respectively. |