Papers with fine-tuning framework
Retrieve Fast, Rerank Smart: Cooperative and Joint Approaches for Improved Cross-Modal Retrieval (2022.tacl-1)
Copied to clipboard
| Challenge: | Current approaches to cross-modal retrieval process text and visual input jointly . current approaches are pretrained from scratch and suffer from huge retrieval latency and inefficiency issues . |
| Approach: | They propose a cooperative retrieve-and-rerank framework that turns pretrained text-image multi-modal models into efficient retrieval models. |
| Outcome: | The proposed framework improves retrieval performance over current approaches . it uses twin networks to encode all items of a corpus and a cross-encoder component for a more nuanced ranking . |
SaFER: A Robust and Efficient Framework for Fine-tuning BERT-based Classifier with Noisy Labels (2023.acl-industry)
Copied to clipboard
| Challenge: | Existing noise-handling methods could not improve performance of BERT on noisy datasets . existing methods could only improve performance on noisy data, authors say . |
| Approach: | They propose a fine-tuning framework for BERT-based text classifiers that combats label noises without access to clean data for training or validation. |
| Outcome: | The proposed framework achieves superior performance on multiple text classification benchmarks. |
PrismRAG: Boosting RAG Factuality with Distractor Resilience and Strategized Reasoning (2025.emnlp-industry)
Copied to clipboard
Mohammad Kachuee, Teja Gollapudi, Minseok Kim, Yin Huang, Kai Sun, Xiao Yang, Jiaqi Wang, Nirav Shah, Yue Liu, Aaron Colak, Anuj Kumar, Wen-tau Yih, Xin Luna Dong
| Challenge: | Existing methods to improve factuality of large language models (LLMs) rely on human-engineered instructions. |
| Approach: | They propose a retrieval-augmented generation framework that trains the model with distractor-aware QA pairs mixing gold evidence with subtle distractor passages and instills reasoning-centric habits that make the LLM plan, rationalize, and synthesize without extensive human engineered instructions. |
| Outcome: | The proposed framework outperforms state-of-the-art solutions across 12 open-book RAG QA benchmarks and is being deployed in production. |
Rigid Formats Controlled Text Generation (2020.acl-main)
Copied to clipboard
| Challenge: | Neural text generation is a challenging task that requires rigid formats to be controlled . a framework called SongNet is designed to tackle this problem . |
| Approach: | They propose a framework to tackle a task called rigid formats controlled text generation . they propose rhyming schemes and a transformer-based auto-regressive language model to improve the modeling performance . |
| Outcome: | The proposed framework improves the performance on format, rhyme, and sentence integrity. |
XDoc: Unified Pre-training for Cross-Format Document Understanding (2022.findings-emnlp)
Copied to clipboard
| Challenge: | Existing pre-trained models target one document format at a time, making it difficult to combine knowledge from multiple document formats. |
| Approach: | They propose a unified pre-trained model which deals with different document formats in a single model. |
| Outcome: | The proposed model achieves comparable or even better performance on a variety of downstream tasks compared with the individual pre-trained models. |
UEGP: Unified Expert-Guided Pre-training for Knowledge Rekindle (2024.findings-naacl)
Copied to clipboard
Yutao Mou, Kexiang Wang, Jianhe Lin, Dehong Ma, Jun Fan, Daiting Shi, Zhicong Cheng, Gu Simiu, Dawei Yin, Weiran Xu
| Challenge: | Existing paradigms for pre-training and fine-tuning have limitations . knowledge rekindle aims to break through performance upper bounds of experts without introducing additional annotated data. |
| Approach: | They propose a new paradigm for pre-training and fine-tuning that aims to re-incorporate the fine- tuned expert model into the training cycle and break through performance upper bounds of experts. |
| Outcome: | The proposed model breaks through performance upper bounds of experts without additional annotated data. |
MeMoTune: A Measure and Moment-Driven Fine-Tuning Framework for Quantized Large Language Models (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing methods combine quantization with parameter-efficient fine-tuning but fail to meet practical performance requirements. |
| Approach: | They propose a measure and moment approach to optimize objective function for superior fine-tuning results by scaling the update process through a gradient. |
| Outcome: | The proposed framework outperforms state-of-the-art methods on tasks like text generation, summarization, and understanding. |
G-Tuning: Improving Generalization of Pre-trained Language Models with Generative Adversarial Network (2023.findings-acl)
Copied to clipboard
| Challenge: | Empirical evaluations on the GLUE benchmark demonstrate that fine-tuning can enhance the generalization performance of pre-trained language models (PLMs) in downstream tasks. |
| Approach: | They propose a fine-tuning framework that transforms the latent representation of pre-trained language models from a universal space to a target space and integrates a generative adversarial network into the fine-untun process. |
| Outcome: | Empirical evaluations on the GLUE benchmark and two additional demanding scenarios show that the proposed framework can improve the generalization performance of pre-trained language models (PLMs) in downstream tasks. |
MALoRA: Mixture of Asymmetric Low-Rank Adaptation for Enhanced Multi-Task Learning (2025.findings-naacl)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) can be fine-tuned to new tasks, but in multi-task scenarios, training imbalance and seesaw effect often arise. |
| Approach: | They propose a flexible fine-tuning framework that leverages asymmetric optimization among LoRA experts to reduce training imbalance and improve performance. |
| Outcome: | The proposed framework outperforms baseline methods in inter- and intra-task learning scenarios. |
ARK: Answer-Centric Retriever Tuning via KG-augmented Curriculum Learning (2026.acl-long)
Copied to clipboard
| Challenge: | Retrieval-Augmented Generation (RAG) is a powerful framework for knowledge-intensive tasks, but its effectiveness in long-context scenarios is often bottlenecked by the retriever’s inability to distinguish sparse yet crucial evidence. |
| Approach: | They propose a framework that fine-tunes the retriever for Answer Alignment by identifying high-quality positive chunks by evaluating their sufficiency to generate the correct answer. |
| Outcome: | The proposed framework improves 14.5% over the base model and maintains strong efficiency for long-context RAG. |
Focus on What Matters: Enhancing Medical Vision-Language Models with Automatic Attention Alignment Tuning (2025.acl-long)
Copied to clipboard
| Challenge: | Existing methods rely on inference-time interventions, which are limited in attention adaptation or require additional supervision. |
| Approach: | They propose a framework for automatic attention alignment tuning that leverages weak labels from SAM and selectively modifies visually-critical attention heads to improve alignment while minimizing interference. |
| Outcome: | The proposed framework outperforms state-of-the-art models on medical VQA and report generation benchmarks. |
Adaptive Cross-lingual Text Classification through In-Context One-Shot Demonstrations (2024.naacl-long)
Copied to clipboard
| Challenge: | Zero-Shot Cross-lingual transfer (ZS-XLT) uses a model trained in a source language to make predictions in another language, often with a performance loss. |
| Approach: | They propose a new approach that uses In-Context Tuning to train a model to learn from context examples and adapt it to a target language by prepending a One-Shot context demonstration. |
| Outcome: | The proposed approach outperforms prompt-based models in Zero-Shot and Few-shot scenarios with target-language examples. |
FewshotQA: A simple framework for few-shot learning of question answering tasks using pre-trained text-to-text models (2021.emnlp-main)
Copied to clipboard
| Challenge: | Existing pre-trained models need fine-tuning on tens of thousands of examples to achieve good results. |
| Approach: | They propose a framework that leverages pre-trained text-to-text models and aligns them with their pre-training framework. |
| Outcome: | The proposed framework outperforms the XLM-Roberta-large on multiple QA benchmarks and is applicable to multilingual situations. |
“In-Dialogues We Learn”: Towards Personalized Dialogue Without Pre-defined Profiles through In-Dialogue Learning (2024.emnlp-main)
Copied to clipboard
| Challenge: | Existing approaches to personalized dialogue generate pre-defined profiles that are time-consuming and labor-intensive to create. |
| Approach: | They propose a framework that leverages dialogue history to characterize personas without pre-defined profiles. |
| Outcome: | The proposed framework improves BLEU and ROUGE scores on three datasets and human evaluations further validate the proposed method. |
Agentic-R1: Distilled Dual-Strategy Reasoning (2025.emnlp-main)
Copied to clipboard
| Challenge: | Current long chain-of-thought models rely on slow and error-prone natural language traces. |
| Approach: | They propose a framework that distills complementary reasoning strategies from multiple teachers into a unified student model. |
| Outcome: | The proposed framework improves accuracy on computation-intensive tasks and reduces inference latency on standard benchmarks. |
Controlling Distributional Bias in Multi-Round LLM Generation via KL-Optimized Fine-Tuning (2026.acl-long)
Copied to clipboard
| Challenge: | Existing evaluation methods focus on single-round inference, but this view is problematic in real-world applications. |
| Approach: | They propose a framework that couples Steering Token Calibration with Semantic Alignment to ensure that LLMs are correctly aligned across gender, race, and sentiment. |
| Outcome: | The proposed framework outperforms baseline methods in achieving precise distributional control in attribute generation tasks. |
MobiZO: Enabling Efficient LLM Fine-Tuning at the Edge via Inference Engines (2025.emnlp-main)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) are currently pre-trained and fine-tuned on large cloud servers . fine-timing on resource-constrained edge devices presents significant memory and computational demands . |
| Approach: | They propose a resource-efficient fine-tuning framework for LLMs specifically designed for edge devices. |
| Outcome: | Experiments show that MobiZO achieves substantial runtime speedups and memory savings while improving fine-tuning accuracy. |
ADVICE: Answer-Dependent Verbalized Confidence Estimation (2026.acl-long)
Copied to clipboard
| Challenge: | Recent advances in large language models (LLMs) have enabled them to communicate their confidence in natural language, improving transparency and reliability. |
| Approach: | They propose a framework that promotes answer-grounded confidence estimation and analyze the dynamics of verbalized confidence estimation. |
| Outcome: | The proposed framework significantly improves confidence calibration while exhibiting strong generalization to unseen settings without degrading task performance. |
TicTac: Time-aware Supervised Fine-tuning for Automatic Text Dating (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing models that ignore the temporal relatedness of documents are time-agnostic and therefore fail to perform in automatic text dating. |
| Approach: | They propose a supervised fine-tuning model for automatic text dating that captures temporal semantic information and uses a contrastive learning-based approach to model two types of temporal relations of diachronic documents. |
| Outcome: | The proposed model outperforms state-of-the-art models on two diachronic corpora and captures temporal semantic information. |
DEFT-UCS: Data Efficient Fine-Tuning for Pre-Trained Language Models via Unsupervised Core-Set Selection for Text-Editing (2024.emnlp-main)
Copied to clipboard
| Challenge: | Recent advances in language modelling have led to the availability of many pre-trained language models (PLMs); however, how much data is needed to fine-tune PLMs for downstream tasks? |
| Approach: | They propose a data-efficient fine-tuning framework that leverages unsupervised core-set selection to identify a smaller, representative dataset to fine- tune PLMs for text-editing tasks. |
| Outcome: | The proposed framework is as accurate as CoEDIT across eight different datasets consisting of six different editing tasks, while finetuning on 70% less data. |
Logit Space Constrained Fine-Tuning for Mitigating Hallucinations in LLM-Based Recommender Systems (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing LLM-based recommender systems rely on standard fine-tuning methodologies, often ignoring hallucination issues during the fine-uning process. |
| Approach: | They propose a logit space constraint-based fine-tuning framework to mitigate hallucination in LLM-based recommenders by incorporating Kullback–Leibler divergence into the training objective. |
| Outcome: | Experiments on two recommendation models with distinct LLM backbones and four real-world datasets show that LCFT reduces hallucination and enhances recommendation performance. |
Parameter Importance is Not Static: Evolving Parameter Isolation for Supervised Fine-Tuning (2026.acl-long)
Copied to clipboard
Zekai Lin, Chao Xue, Di Liang, Xingsheng Han, Peiyang Liu, Xianjie Wu, Lei Jiang, Yu Lu, Bob Simons, Shuang Liang, Minlong Peng
| Challenge: | Recent approaches to fine-tuning of large language models suffer from task interference and catastrophic forgetting. |
| Approach: | They propose a fine-tuning framework that adapts isolation decisions based on online estimates of parameter importance. |
| Outcome: | The proposed framework reduces interference and forgetting while releasing outdated parameters to recover plasticity. |
TLPO: Token-Level Policy Optimization for Mitigating Language Confusion in Large Language Models (2026.acl-long)
Copied to clipboard
| Challenge: | Prior mitigation approaches that optimize entire responses operate at the level of entire responses and can lead to unintended degradation of general model capabilities. |
| Approach: | They propose a fine-tuning framework to mitigate erroneous outputs by localizing and updating the policy at a granular level. |
| Outcome: | The proposed framework outperforms baselines on multiple multilingual LLMs across diverse languages while preserving task accuracy. |