Papers with text-generation tasks
Are Large Language Model-based Evaluators the Solution to Scaling Up Multilingual Evaluation? (2024.findings-eacl)
Copied to clipboard
Rishav Hada, Varun Gumma, Adrian Wynter, Harshita Diddee, Mohamed Ahmed, Monojit Choudhury, Kalika Bali, Sunayana Sitaram
| Challenge: | Large Language Models (LLMs) excel in various tasks, but their evaluation, especially in languages beyond the top 20, remains inadequate due to existing benchmarks and metrics limitations. |
| Approach: | They propose to use Large Language Models as evaluators to rank or score other models’ outputs by calibrating them against 20K human judgments across three text-generation tasks, five metrics, and eight languages. |
| Outcome: | The proposed evaluation methods can be used to improve multilingual evaluation by calibrating them against 20K human judgments across three text-generation tasks, five metrics, and eight languages. |
Frustratingly Easy Model Ensemble for Abstractive Summarization (D18-1)
Copied to clipboard
| Challenge: | Existing studies on compressing or distilling ensemble models have shown that they increase computational costs and reduce performance. |
| Approach: | They propose an unsupervised method that combines multiple models by selecting a majority-like output in post-processing. |
| Outcome: | The proposed method performs better than the current ensemble methods on a news-headline-generation task. |
Enhancing High-order Interaction Awareness in LLM-based Recommender Model (2024.emnlp-main)
Copied to clipboard
| Challenge: | Existing approaches to model user-item interactions do not account for high-order interactions. |
| Approach: | They propose to enhance whole-word embeddings to enhance LLMs’ interpretation of graph-constructed interactions for recommendations without requiring graph pre-training. |
| Outcome: | The proposed model outperforms state-of-the-art methods in direct recommendations. |
Re-evaluating Evaluation in Text Summarization (2020.emnlp-main)
Copied to clipboard
| Challenge: | Automated evaluation metrics are an essential part of the development of text-generation tasks such as summarization. |
| Approach: | They propose to use top-scoring system outputs to assess the reliability of automatic evaluation metrics for text summarization. |
| Outcome: | The proposed evaluation method is based on human judgments from 25 top-scoring neural summarization systems. |
Adaptive Contrastive Search: Uncertainty-Guided Decoding for Open-Ended Text Generation (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Existing approaches to decode text to the most probable sequence have been proposed to address these challenges by improving coherence, diversity, and resemblance to human-generated text. |
| Approach: | They propose a novel decoding strategy that extends contrastive search by incorporating an adaptive degeneration penalty informed by the model’s estimated uncertainty at each generation step. |
| Outcome: | The proposed approach improves creativity and coherence while maintaining coherency across model architectures, languages, and datasets. |
Improving Automatic Evaluation of Large Language Models (LLMs) in Biomedical Relation Extraction via LLMs-as-the-Judge (2025.acl-long)
Copied to clipboard
| Challenge: | Large Language Models generate human-like text, making them unreliable for biomedical relation extraction tasks. |
| Approach: | They propose to use Large Language Models as judges to evaluate biomedical relation extraction . they propose structured output formatting for LLM-generated responses that helps LLMs improve their performance by 15%. |
| Outcome: | The proposed method improves LLM-Judges' performance by 15% . it is cheaper and more efficient than human evaluation metrics, the authors say . |