Challenge: Increasing demand for training data is causing language models to be trained on synthetic data, a new study finds . fine-tuning models on synthetic datasets reduces self-preference bias .
Approach: They investigate the impact of diversity of synthetic data on fine-tuned large language models.
Outcome: The proposed model can mitigate distribution collapse, maintain diversity of output distribution, and reduce self-preference bias.

Similar Papers

The Effect of Language Diversity When Fine-Tuning Large Language Models for Translation (2025.findings-emnlp)

Copied to clipboard

Challenge: Prior research on language diversity in LLM fine-tuning has reported benefits while others find no benefits.
Approach: They find that expanding language diversity during fine-tuning improves translation quality . they also show that increased language diversity creates more language-agnostic representations .
Outcome: The proposed model improves translation quality for unsupervised and supervised pairs . the results plateau or decrease beyond a certain diversity threshold.
Improving the OOD Performance of Closed-Source LLMs on NLI Through Strategic Data Selection (2026.findings-eacl)

Copied to clipboard

Challenge: Existing methods to improve robustness require changing the fine-tuning process or large-scale data augmentation, which are infeasible or cost prohibitive for closed-source models.
Approach: They propose to prioritize more complex examples or replace existing training examples with LLM-generated data to improve performance on OOD NLI datasets.
Outcome: The proposed methods improve performance on difficult OOD datasets while training with synthetic data leads to substantial improvements on easier OOD data.
LLM See, LLM Do: Leveraging Active Inheritance to Target Non-Differentiable Objectives (2024.emnlp-main)

Copied to clipboard

Challenge: Historically, high-quality labeled data has been costly to curate due to scarcity of available data and financial cost.
Approach: They characterize the impact of passive inheritance of model properties by studying how the source of synthetic data shapes models’ internal biases, calibration and preferences, and their generations’ textual attributes.
Outcome: The proposed model inheritance can increase lexical diversity or reduce toxicity.
Scaling Data Diversity for Fine-Tuning Language Models in Human Alignment (2024.lrec-main)

Copied to clipboard

Challenge: Large language models (LLMs) can reveal toxic or offensive content inadvertently or intentionally.
Approach: They propose to control the diversity of both sides according to the number of samples for fine-tuning, which can directly reflect their impact.
Outcome: The proposed approach improves the performance of large language models after fine-tuning.
I Learn Better If You Speak My Language: Understanding the Superior Performance of Fine-Tuning Large Language Models with LLM-Generated Responses (2024.emnlp-main)

Copied to clipboard

Challenge: Recent research has demonstrated that a large language model (LLM) can generate training data for another LLM, or for creating supplementary training materials, such as rationales.
Approach: They conduct an in-depth investigation to understand why fine-tuning an LLM with responses generated by a LLM often yields better results than using responses generated from humans.
Outcome: The proposed approach can be used to transfer knowledge from a larger model to a smaller one, or for creating supplementary training materials, such as rationales.
Seed-Free Synthetic Data Generation Framework for Instruction-Tuning LLMs: A Case Study in Thai (2024.acl-srw)

Copied to clipboard

Challenge: Xue et al., 2024) have demonstrated that large language models can perform at human level across multitudes of tasks and domains.
Approach: They propose a seed-free framework for generating synthetic instruction-tuning data that incorporates fluency, diversity, and cultural context.
Outcome: The proposed framework achieves competitive performance using only 5,000 instructions compared to state-of-the-art Thai LLMs trained on hundreds of thousands of instructions.
On LLMs-Driven Synthetic Data Generation, Curation, and Evaluation: A Survey (2024.findings-acl)

Copied to clipboard

Challenge: Large Language Models (LLMs) provide a data-centric solution to alleviate limitations of real-world data with synthetic data generation.
Approach: They propose a generic workflow for LLM-driven synthetic data generation.
Outcome: The proposed workflows highlight gaps in existing research and outline avenues for future studies.
Towards Implicit Bias Detection and Mitigation in Multi-Agent LLM Interactions (2024.findings-emnlp)

Copied to clipboard

Challenge: a recent study shows that large language models are susceptible to societal biases due to their exposure to human-generated data.
Approach: They propose two strategies to mitigate implicit gender biases in large language models . they create scenarios where implicit gender is present and develop a metric to assess the presence of biase .
Outcome: The proposed methods mitigate implicit biases with self-reflection and fine-tuning.
Scaling Low-Resource MT via Synthetic Data Generation with LLMs (2025.emnlp-main)

Copied to clipboard

Challenge: a recent study has shown that LLM-generated synthetic data can improve low-resource machine translation performance . traditional data augmentation techniques like back-translation preserve the human-written target and synthesize the other .
Approach: They construct a document-level synthetic corpus from English Europarl and extend it via pivoting to 147 additional language pairs.
Outcome: The proposed model can significantly improve low-resource machine translation performance even when noisy.
Fine-tuning Large Language Models with Limited Data: A Survey and Practical Guide (2026.tacl-1)

Copied to clipboard

Challenge: Pre-trained language models provide strong foundations, but effective adaptation under data scarcity requires efficient and efficient fine-tuning techniques.
Approach: They propose to review parameter-efficient fine-tuning techniques that lower training and deployment costs and domain and cross-lingual adaptation methods for both encoder and decoder models.
Outcome: The proposed techniques lower training and deployment costs, domain and cross-lingual adaptation methods, and model specialization strategies.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations