Papers by Haw-Shiuan Chang
LLM Self-Correction with DeCRIM: Decompose, Critique, and Refine for Enhanced Following of Instructions with Multiple Constraints (2024.findings-emnlp)
Copied to clipboard
Thomas Palmeira Ferraz, Kartik Mehta, Yu-Hsiang Lin, Haw-Shiuan Chang, Shereen Oraby, Sijia Liu, Vivek Subramanian, Tagyoung Chung, Mohit Bansal, Nanyun Peng
| Challenge: | Recent studies have shown that LLMs struggle with instructions containing multiple constraints. |
| Approach: | They propose a self-correction pipeline that decomposes the original instruction into a list of constraints and uses a Critic model to decide when and where the LLM’s response needs refinement. |
| Outcome: | The proposed model outperforms GPT-4 on RealInstruct and IFEval even with weak feedback. |
Multi-CLS BERT: An Efficient Alternative to Traditional Ensembling (2023.acl-long)
Copied to clipboard
| Challenge: | ensembling BERT models often improves accuracy but at the cost of significantly more computation and memory footprint. |
| Approach: | They propose a new ensembling method for CLS-based prediction tasks that is almost as efficient as a single BERT model. |
| Outcome: | The proposed method outperforms existing BERT models on GLUE and SuperGLUE with 100 training samples. |
Revisiting the Architectures like Pointer Networks to Efficiently Improve the Next Word Distribution, Summarization Factuality, and Beyond (2023.findings-acl)
Copied to clipboard
| Challenge: | Existing solutions for word probability distributions are limited and the output softmax layer is inherently limited. |
| Approach: | They propose to use the output softmax layer to compute the word probability distribution instead of using pointer networks to break the bottleneck. |
| Outcome: | The proposed method improves factCC score by 2 points in CNN/DM and XSUM dataset, and MAUVE scores by 30% in bookSum paragraph-level dataset. |
Explaining and Improving Contrastive Decoding by Extrapolating the Probabilities of a Huge and Hypothetical LM (2024.emnlp-main)
Copied to clipboard
| Challenge: | Contrastive decoding (CD) improves the next-token distribution of a large expert language model (LM) using a small amateur LM. |
| Approach: | They propose a new unsupervised decoding method called Asymptotic Probability Decoding (APD) that extrapolates the probability curves from the LMs of different sizes to infer the asymptototic probabilities from an infinitely large LM. |
| Outcome: | The proposed method improves the next-token distribution of a large expert language model using a small amateur LM. |
Distributional Inclusion Vector Embedding for Unsupervised Hypernymy Detection (N18-1)
Copied to clipboard
| Challenge: | Existing unsupervised methods for learning hypernyms from unlabeled text are not scaled to large vocabularies or yield unacceptably poor accuracy. |
| Approach: | They propose an unsupervised method of hypernym discovery using word contexts . they use word2vec to embed word context distributions without supervision . |
| Outcome: | The proposed method provides double the precision and highest average performance on 11 datasets. |
Multi-facet Universal Schema (2021.eacl-main)
Copied to clipboard
| Challenge: | Existing methods to solve relation extraction tasks violate USchema's assumption that sentence patterns that share the same entity pairs are similar to each other. |
| Approach: | They propose a multi-facet universal schema that embeds multiple sentence patterns as facets and encourages one to be close to that of another if they co-occur with the same entity pair. |
| Outcome: | The proposed model outperforms its single-facet embedding counterpart in relation extraction tasks. |
Open Aspect Target Sentiment Classification with Natural Language Prompts (2021.emnlp-main)
Copied to clipboard
| Challenge: | Existing aspects target sentiment classification models are not trainable if annotated data are not available. |
| Approach: | They propose an approach that solves ATSC with natural language prompts by 24.13 accuracy points and 33.14 macro F1 points. |
| Outcome: | The proposed model outperforms supervised SOTA approaches under few-shot scenarios and under supervised settings, especially for few-shot cases. |
Changing the Mind of Transformers for Topically-Controllable Language Generation (2021.eacl-main)
Copied to clipboard
| Challenge: | Existing interactive writing assistants do not allow authors to guide text generation in desired topical directions. |
| Approach: | They propose a framework that displays multiple candidate upcoming topics and generates a text generation model that adheres to the chosen topics. |
| Outcome: | The proposed model generates fluent sentences related to the selected topics, as judged by automated metrics and crowdsourced workers. |
Softmax Bottleneck Makes Language Models Unable to Represent Multi-mode Word Distributions (2022.acl-long)
Copied to clipboard
| Challenge: | Existing language models can't predict the probability distribution over next words or masked words because of a single hidden state. |
| Approach: | They propose a multi-facet softmax to address the limitations of softmax . they propose LMs that can predict the next word distribution better as their sizes grow . |
| Outcome: | The proposed model achieves two-fold improvements in the perplexity of GPT-2 and BERT. |