| Challenge: | a recent demonstration of the power of huge language models such as GPT-2 to memorise the answers to factoid questions raises questions about the extent to which knowledge is embedded directly within these large models. |
| Approach: | They propose to use unsupervised learning techniques to add knowledge explicitly without extensive training. |
| Outcome: | The proposed architecture allows for explicit addition of knowledge without extensive training. |
Similar Papers
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. |
Elaboration-Generating Commonsense Question Answering at Scale (2023.acl-long)
Copied to clipboard
| Challenge: | elaborations are generated using language models that generate background knowledge that helps improve performance . human evaluations show that the quality of the generated ellaborations is high . |
| Approach: | They propose to finetune smaller language models to generate useful intermediate context . they compare a language model with an answer predictor and generate elaborations . human evaluations show that the quality of the generated ellaborations is high . |
| Outcome: | The proposed framework outperforms other models on commonsense questions on four commons sense benchmarks. |
Factuality of Large Language Models: A Survey (2024.emnlp-main)
Copied to clipboard
Yuxia Wang, Minghan Wang, Muhammad Arslan Manzoor, Fei Liu, Georgi Georgiev, Rocktim Das, Preslav Nakov
| Challenge: | Large language models (LLMs) are factually incorrect, which limits their applicability in real-world scenarios. |
| Approach: | They analyze existing work to identify major challenges and their associated causes . they propose to evaluate LLMs using a variety of measures to mitigate factual errors . |
| Outcome: | The proposed methods are based on a variety of datasets and proposed strategies to mitigate factual errors. |
Strong Baselines for Simple Question Answering over Knowledge Graphs with and without Neural Networks (N18-2)
Copied to clipboard
| Challenge: | Existing work on simple question answering over knowledge graphs involves increasingly complex NN architectures. |
| Approach: | They propose to decompose the problem into entity detection, entity linking, relation prediction, evidence combination and heuristics. |
| Outcome: | The proposed approach outperforms existing models and benchmarks on a simple QA task. |
Eliciting Knowledge from Large Pre-Trained Models for Unsupervised Knowledge-Grounded Conversation (2022.emnlp-main)
Copied to clipboard
| Challenge: | Recent advances in large-scale pre-training provide large models with the potential to learn knowledge from the raw text. |
| Approach: | They propose a posterior-based reweighing and noisy training strategy to exploit generated knowledge in dialogue generation. |
| Outcome: | Empirical results show that the proposed methods outperform the state-of-the-art methods in unsupervised knowledge-grounded conversation. |
A guide to the dataset explosion in QA, NLI, and commonsense reasoning (2020.coling-tutorials)
Copied to clipboard
| Challenge: | a tutorial aims to provide an up-to-date guide to the recent datasets . the target audience is the NLP practitioners who are lost in dozens of the recent data sets. |
| Approach: | This tutorial provides an up-to-date guide to the recent datasets . it surveys old and new methodological issues with dataset construction . |
| Outcome: | This tutorial aims to provide an up-to-date guide to the recent datasets . it surveys the old and new methodological issues with dataset construction . |
It’s Not Just Size That Matters: Small Language Models Are Also Few-Shot Learners (2021.naacl-main)
Copied to clipboard
| Challenge: | Pretraining ever-larger language models on massive corpora requires enormous amounts of compute. |
| Approach: | They propose to convert textual inputs into cloze questions that contain a task description . they also exploit unlabeled data to improve their performance . |
| Outcome: | The proposed model outperforms GPT-3 with PET/iPET with cloze questions and unlabeled data. |
Reimagining Retrieval Augmented Language Models for Answering Queries (2023.findings-acl)
Copied to clipboard
Wang-Chiew Tan, Yuliang Li, Pedro Rodriguez, Richard James, Xi Victoria Lin, Alon Halevy, Wen-tau Yih
| Challenge: | Large language models (LLMs) are expensive to train, deploy, and maintain, both financially and in terms of environmental impact. |
| Approach: | They present a reality check on large language models and compare their predictions to retrieval-augmented language models. |
| Outcome: | The proposed models fare better on question answering tasks and have become the foundation of impressive demos like Chat-GPT. |
Paraphrasing with Large Language Models (D19-56)
Copied to clipboard
| Challenge: | Recent work has shown large language models are adept at text generation and fine-tuning for downstream NLP tasks. |
| Approach: | They propose a system that generates paraphrased examples in autoregressive fashion using a neural network without the need for techniques such as top-k word selection or beam search. |
| Outcome: | The proposed system generates paraphrased examples in autoregressive fashion without the need for techniques such as top-k word selection or beam search. |
Evaluating Large Language Models on Controlled Generation Tasks (2023.emnlp-main)
Copied to clipboard
Jiao Sun, Yufei Tian, Wangchunshu Zhou, Nan Xu, Qian Hu, Rahul Gupta, John Wieting, Nanyun Peng, Xuezhe Ma
| Challenge: | Recent studies have looked into the ability of large language models in various benchmark tasks, including question generation, reading comprehension, multilingual and etc. However, few studies investigate the controllability of large languages. |
| Approach: | They propose to compare large language models with state-of-the-start finetuned smaller models to find that large language model controls are comparable to smaller models. |
| Outcome: | The proposed model can meet hard constraints and perform better than state-of-the-art models. |