Papers with direct fine-tuning
Recycling a Pre-trained BERT Encoder for Neural Machine Translation (D19-56)
Copied to clipboard
| Challenge: | In monolingual tasks, the number of unlearned model parameters is as huge as the number learned parameters in the BERT model. |
| Approach: | They propose to apply a pre-trained Bidirectional Encoder Representations from Transformers (BERT) model to Transformer-based neural machine translation (NMT) based on the Transformer. |
| Outcome: | The proposed model is stable and efficient in low-resource settings. |
Exploring Cross-lingual Text Detoxification with Large Multilingual Language Models. (2022.acl-srw)
Copied to clipboard
| Challenge: | Existing methods of textual style transfer are monolingual i.e. designed to work in one exact language. |
| Approach: | They propose to make large multilingual models capable of performing multilingual style transfer without direct fine-tuning in a given language. |
| Outcome: | The proposed model can generate text in a given language without fine-tuning and is able to perform cross-lingual detoxification without direct fine- tuning. |
When Format Changes Meaning: Investigating Semantic Inconsistency of Large Language Models (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Large language models are vulnerable to semantic inconsistency, a study finds . minor formatting variations result in divergent predictions for semantically equivalent inputs. |
| Approach: | They evaluate LLMs for semantic inconsistency and find they remain vulnerable . they propose to use mechanistic analysis to develop models that improve their reliability . |
| Outcome: | The proposed model is vulnerable to semantic inconsistency, the authors show . their model is brittle even in state-of-the-art models, they say . |
Inference-Time Language Model Alignment via Integrated Value Guidance (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Large language models are fine-tuned to align with human preferences, but tuning large models is computationally intensive and complex. |
| Approach: | They propose a method that uses implicit and explicit value functions to guide language model decoding at token and chunk-level respectively. |
| Outcome: | The proposed method outperforms traditional methods and circumvents the complexities of fine-tuning. |
GIFT: Guided Fine-Tuning and Transfer for Enhancing Instruction-Tuned Language Models (2026.acl-long)
Copied to clipboard
Zhiwen Ruan, Yichao Du, Jianjie Zheng, Longyue Wang, Yun Chen, Peng Li, Jinsong Su, Yang Liu, Guanhua Chen
| Challenge: | Existing adapter-based transfer methods treat instruction-tuned models as passive targets . direct fine-tuning can disrupt this delicate balance and lead to instability or performance degradation. |
| Approach: | They propose a framework that incorporates instruction-level guidance into task adaptation. |
| Outcome: | The proposed framework outperforms direct fine-tuning and representative transfer-based baselines while maintaining robust generalization and favorable test-time scaling behavior. |
AdaMergeX: Cross-Lingual Transfer with Large Language Models via Adaptive Adapter Merging (2025.naacl-long)
Copied to clipboard
| Challenge: | Large Language Models excel in highresource languages but underperform in lowresource ones. |
| Approach: | They propose a cross-lingual transfer method that decouples "task ability" from "language ability" they propose to use adaptive adapter merging to obtain target adapters by combining other adapters. |
| Outcome: | The proposed method outperforms existing methods in highresource languages . it decouples "task ability" from "language ability" but fails to fully separate "task capability" from the "source language" |
Generalizable LLM Learning of Graph Synthetic Data with Post-training Alignment (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing research has focused on enhancing graph reasoning capabilities of LLMs by supervised fine-tuning on synthetic graph data. |
| Approach: | They propose to unlock generalizable learning of graph with post-training alignment with synthetic graph data by aligning off-the-shelf LLMs and LLM fine-tuned on synthetic graphs. |
| Outcome: | The proposed algorithm improves on synthetic graph problems and out-of-domain tasks with implicit graph structures. |
DEFT: Distribution-guided Efficient Fine-Tuning for Human Alignment (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Experimental results show that the methods enhanced by DEFT outperform the original methods in both alignment capability and generalization ability, with significantly reduced training time. |
| Approach: | They propose a distribution-based alignment framework that integrates data filtering and distributional guidance to improve alignment efficiency and generalization ability. |
| Outcome: | The proposed framework outperforms existing methods in alignment capability and generalization ability with significantly reduced training time. |
Selective Prompting Tuning for Personalized Conversations with LLMs (2024.findings-acl)
Copied to clipboard
| Challenge: | Personalization in conversational AI requires persona profiles and contextual understanding to create meaningful conversations. |
| Approach: | They propose a method that softly prompts LLMs for personalized conversations in a selective way. |
| Outcome: | The proposed approach improves response diversity by up to 90% on the CONVAI2 dataset. |