Challenge: ATLANTIS is a new technique to improve the performance of large language models.
Approach: They propose a new technique to bridge the gap between the distribution of current datasets and the real-world data distribution by using importance sampling.
Outcome: The proposed technique can bring consistent and significant improvements to models’ performance and can be flexibly transferred among models with different structures.

Similar Papers

ProFit: Leveraging High-Value Signals in SFT via Probability-Guided Token Selection (2026.findings-acl)

Copied to clipboard

Challenge: Traditional fine-tuning ignores one-to-many nature of language, leading to overfitting . authors propose a method to fine- tune LLMs by leveraging tokens.
Approach: They propose a method to fine-tune Large Language Models by leveraging tokens to mask low-probability tokens.
Outcome: The proposed method outperforms baselines on general reasoning and mathematical benchmarks.
Massive Supervised Fine-tuning Experiments Reveal How Data, Layer, and Training Factors Shape LLM Alignment Quality (2025.emnlp-main)

Copied to clipboard

Challenge: Recent advances in large language models (LLMs) have greatly improved natural language understanding and generation.
Approach: They train a wide range of base models on a variety of datasets including code generation, mathematical reasoning, and general-domain tasks.
Outcome: The results show that training–task synergies persist across all models while others vary substantially, emphasizing the importance of model-specific strategies.
Not All Parameters Are Created Equal: Smart Isolation Boosts Fine-Tuning Performance (2025.emnlp-main)

Copied to clipboard

Challenge: Extensive experiments demonstrate that our approach significantly alleviates task interference and forgetting.
Approach: They propose a framework for supervised fine-tuning for large language models . they first fine-tail the model on each task to identify its core parameter regions .
Outcome: The proposed framework outperforms vanilla fine-tuning and baselines on multiple public benchmarks on reasoning, dialogue, instruction following, and more.
Weaker Than You Think: A Critical Look at Weakly Supervised Learning (2023.acl-long)

Copied to clipboard

Challenge: Weakly supervised learning is a popular approach for training machine learning models in low-resource settings.
Approach: They propose to use weakly supervised learning to train models with noisy labels from weak sources instead of collecting expensive human annotations.
Outcome: The proposed methods outperform weakly supervised methods on various NLP datasets and tasks on the test sets.
How Abilities in Large Language Models are Affected by Supervised Fine-tuning Data Composition (2024.acl-long)

Copied to clipboard

Challenge: supervised fine-tuning (SFT) is a technique used to enhance multiple abilities in large language models.
Approach: They propose to study the interplay of data composition between mathematical reasoning, code generation, and general human-aligning abilities during supervised fine-tuning.
Outcome: The proposed model improves math reasoning and code generation with increasing data amount . the proposed model size and SFT strategies can be used to learn multiple skills with different scaling patterns.
Layer-wise Importance Matters: Less Memory for Better Performance in Parameter-efficient Fine-tuning of Large Language Models (2024.findings-emnlp)

Copied to clipboard

Challenge: Parameter-Efficient Fine-Tuning (PEFT) methods have gained popularity for adapting pre-trained Large Language Models (LLMs) to downstream tasks.
Approach: They propose a method to optimize the importance of full layers with layer-wise importance scoring by leveraging the estimated importance scores.
Outcome: The proposed method is compatible with PEFT methods that operate on a per-layer basis and achieves better performance.
Rethinking Data Selection at Scale: Random Selection is Almost All You Need (2025.findings-emnlp)

Copied to clipboard

Challenge: Existing data selection techniques are designed for small data pools, a study finds . filtering data by token length is an efficient method for improving results .
Approach: They use self-scoring methods that do not rely on external help to perform fine-tuning . they also find that filtering data by token length offers a stable and efficient method .
Outcome: The proposed methods outperform random selection on large datasets on large data pools.
META-LORA: Memory-Efficient Sample Reweighting for Fine-Tuning Large Language Models (2025.coling-main)

Copied to clipboard

Challenge: Supervised fine-tuning (SFT) is widely adopted for tailoring large language models (LLMs) to specific downstream tasks.
Approach: They propose a memory-efficient method for automatic sample reweighting that learns to re-weight fine-tuning samples by minimizing the loss on a small, high-quality validation set.
Outcome: Meta-LoRA learns to reweight fine-tuning samples by minimizing the loss on a small, high-quality validation set through an end-to-end bi-level optimization framework based on meta-learning.
A Layer-wise Analysis of Supervised Fine-Tuning (2026.acl-long)

Copied to clipboard

Challenge: Existing methods for fine-tuning ignore depth-dependent heterogeneity of instruction-following . a critical gap remains in understanding where these changes occur across the model's depth and which layers are essential for instruction- following.
Approach: They propose a method which selectively updates critical intermediate layers . they show that effective alignment is architecturally localized rather than distributed .
Outcome: The proposed method outperforms standard LoRA up to 10.2% on GSM8K with reduced parameter overhead.
GRASS: Gradient-based Adaptive Layer-wise Importance Sampling for Memory-efficient Large Language Model Fine-tuning (2026.findings-acl)

Copied to clipboard

Challenge: Low-rank adaptation methods for large language models limit expressiveness and performance . layer-wise fine-tuning methods overlook variations in layer importance across tasks and training stages, resulting in suboptimal performance on downstream tasks.
Approach: They propose a gradient-based adaptive layer-wise importance sampling framework that updates only a subset of parameters to reduce memory usage.
Outcome: The proposed framework outperforms state-of-the-art methods in accuracy and memory usage.

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