BOSE: A Systematic Evaluation Method Optimized for Base Models (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing evaluation methods for large language models (LLMs) are inadequate to provide solid conclusions for key experiments such as data ablation and scaling law. |
| Approach: | They propose a method specifically designed to optimize the evaluation of base models by incorporating two innovations: In-Context Light-instruction Prompt and Blank-ppl for multi-choice tasks with candidate options. |
| Outcome: | The proposed method significantly improves stability and consistency of evaluations during pre-training and consistency between base and instruct models. |
Similar Papers
Where to start? Analyzing the potential value of intermediate models (2023.emnlp-main)
Copied to clipboard
| Challenge: | a finetuned model may be better base models than the vanilla pretrained model . this scheme, often referred to as intertraining, is the focus of the present work . |
| Approach: | They propose a scheme to analyze the potential intertraining gain independently for the target dataset and for a base model being considered as a starting point. |
| Outcome: | The proposed model is strong even if training data was not aligned with target dataset. |
Cost-effective Selection of Pretraining Data: A Case Study of Pretraining BERT on Social Media (2020.findings-emnlp)
Copied to clipboard
| Challenge: | Recent studies show that domain-specific BERT models can be improved when in-domain data is used for pretraining. |
| Approach: | They propose to use Twitter and forum text as pretraining sources for two BERT models and use similarity measures to nominate in-domain data for pretraining. |
| Outcome: | The proposed method can be used to improve performance on downstream tasks by using in-domain data. |
What Really Matters for Table LLMs? A Meta-Evaluation of Model and Data Effects (2026.findings-eacl)
Copied to clipboard
Naihao Deng, Sheng Zhang, Henghui Zhu, Shuaichen Chang, Jiani Zhang, Alexander Hanbo Li, Chung-Wei Hang, Hideo Kobayashi, Yiqun Hu, Patrick Ng
| Challenge: | a series of paradigm shifts have come with distinct characteristics and challenges associated with table modeling. |
| Approach: | They propose to replicate four table LLMs by instruction-tuning three foundation models on four existing datasets. |
| Outcome: | The results show that base model choice plays a more dominant role than training data itself. |
Are LLM-based Evaluators Confusing NLG Quality Criteria? (2024.acl-long)
Copied to clipboard
| Challenge: | Existing studies show that LLMs confuse evaluation criteria, which reduces their reliability. |
| Approach: | They propose a hierarchical classification system for 11 common aspects with corresponding different evaluation criteria. |
| Outcome: | The proposed system is based on 11 common aspects with different evaluation criteria. |
What is the best recipe for character-level encoder-only modelling? (2023.acl-long)
Copied to clipboard
| Challenge: | aims to benchmark recent progress in language understanding models that output contextualised representations at the character level. |
| Approach: | They aim to find the best way to build and train character-level BERT-like models by comparing architectural innovations with pretraining objectives. |
| Outcome: | The proposed model outperforms a token-based model on a set of evaluation tasks with a fixed training procedure. |
A Controlled Reevaluation of Coreference Resolution Models (2024.lrec-main)
Copied to clipboard
| Challenge: | a pretrained language model is used in state-of-the-art coreference resolution models. |
| Approach: | They evaluate five coreference resolution models and control for language model used . they find that encoder-based CR models outperform decoder--based models in accuracy . |
| Outcome: | The encoder-based model outperforms the decoder--based models in accuracy and speed . older model generalizes the best to out-of-domain textual genres . |
Contextual Embeddings: When Are They Worth It? (2020.acl-main)
Copied to clipboard
| Challenge: | In recent years, rich contextual embeddings have enabled rapid progress on benchmarks like GLUE, but require significant computational resources during pretraining and during downstream task training and inference. |
| Approach: | They empirically compare contextual embeddings with classic pretrained embedders and a random word embeddable with a simple baseline. |
| Outcome: | The proposed models perform within 5 to 10% accuracy on industry-scale data. |
The Progress Illusion: Revisiting meta-evaluation standards of LLM evaluators (2025.findings-emnlp)
Copied to clipboard
| Challenge: | LLM judges have gained popularity as an inexpensive and performant substitute for human evaluation. |
| Approach: | They revisit meta-evaluations of LLM evaluators under a setting that more closely aligns with practice by examining evaluers’ ability to distinguish test system pairs that are closer in capability. |
| Outcome: | The proposed meta-evaluation setting is significantly different from the use of human evaluations. |
Benchmarking Meta-embeddings: What Works and What Does Not (2021.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods to build meta-embeddings have been evaluated using a variety of methods and datasets, which makes it difficult to draw meaningful conclusions regarding the merits of each approach. |
| Approach: | They propose a unified framework for a fair and objective meta-embedding evaluation using intrinsic and extrinsic tasks. |
| Outcome: | The proposed framework outperforms existing methods on intrinsic and extrinsic evaluation benchmarks and outperformed existing methods. |
RADDLE: An Evaluation Benchmark and Analysis Platform for Robust Task-oriented Dialog Systems (2021.acl-long)
Copied to clipboard
| Challenge: | Existing task-oriented dialog systems are less than satisfactory in robustness evaluation . existing systems are weak in robustity evaluation based on pre-training and fine-tuning . |
| Approach: | They propose to use a set of training examples to evaluate model generalization ability . they propose to include tasks with limited training data to favor models with strong generalization abilities . |
| Outcome: | The proposed model generalizes well with limited training data and is robust to user input across domains. |