FINE-TUNING LLMS

Genetic Instruct: Scaling up Synthetic Generation of Coding Instructions for Large Language Models (2025.acl-industry)

Challenge:	Parameter-Efficient Fine-Tuning (PEFT) methods address the increasing size of Large Language Models (LLMs).
Approach:	They propose a framework for efficient fine-tuning Large Language Models (LLMs) they aim to train only a small percentage of the full model's parameters .
Outcome:	Xu et al., 2023; Ding e t al, 2024; Lialin e al. 2023) show that using PEFT methods can improve performance.

Copied to clipboard

Somshubra Majumdar, Vahid Noroozi, Mehrzad Samadi, Sean Narenthiran, Aleksander Ficek, Wasi Uddin Ahmad, Jocelyn Huang, Jagadeesh Balam, Boris Ginsburg

Fine-tuning Large Language Models with Limited Data: A Survey and Practical Guide (2026.tacl-1)

Challenge:	Large Language Models (LLMs) require high quality instruction data for effective alignment, especially in code generation tasks where expert curated datasets are expensive to produce.
Approach:	They propose a scalable algorithm for synthesizing large-scale, high quality coding instructions using evolutionary principles.
Outcome:	The proposed approach generates 7.5 million coding instructions with a small seed population and is highly parallelizable and effective even with weaker generator models.

Copied to clipboard

Marton Szep, Daniel Rueckert, Rüdiger von Eisenhart-Rothe, Florian Hinterwimmer

Intention-Adaptive LLM Fine-Tuning for Text Revision Generation (2026.findings-eacl)

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.

Copied to clipboard

Zhexiong Liu, Diane Litman

SeRTS: Self-Rewarding Tree Search for Biomedical Retrieval-Augmented Generation (2024.findings-emnlp)

Challenge:	Existing work on large language models (LLMs) has demonstrated impressive capabilities in context-based text generation tasks, such as summarization and reasoning.
Approach:	They propose an intention-adaptive layer-wise LLM fine-tuning framework that dynamically selects a subset of LLM layers to learn intentions and transfers them to revision generation.
Outcome:	The proposed framework outperforms PEFT baselines on small revision corpora while maintaining fast convergence and accuracy.

Copied to clipboard

Minda Hu, Licheng Zong, Hongru Wang, Jingyan Zhou, Jingjing Li, Yichen Gao, Kam-Fai Wong, Yu Li, Irwin King

Course-Correction: Safety Alignment Using Synthetic Preferences (2024.emnlp-industry)

Challenge:	Existing retrieval-augmented approaches to large language models face performance limitations due to the lack of publicly available training data.
Approach:	They propose a plug-and-play LLM-based retrieval method called Self-Rewarding Tree Search based on Monte Carlo Tree Search and a self-rewarding paradigm to address these limitations.
Outcome:	The proposed method improves the performance of the BM25 retriever and surpasses the baseline of self-reflection in both efficiency and scalability.

Copied to clipboard

Rongwu Xu, Yishuo Cai, Zhenhong Zhou, Renjie Gu, Haiqin Weng, Liu Yan, Tianwei Zhang, Wei Xu, Han Qiu

Responsible & Trustworthy NLP

Challenge:	Recent studies show that large language models generate harmful content, but the potential for generating harmful content is an escalating concern.
Approach:	They propose to fine-tune LLMs with preference learning to emphasize the preference for timely course-correction by using an automated pipeline.
Outcome:	The proposed model improves course-correction skills without affecting general performance and resists jailbreak attacks.

Contrastive Perplexity for Controlled Generation: An Application in Detoxifying Large Language Models (2025.acl-long)

Copied to clipboard

Tassilo Klein, Moin Nabi

Are Large Language Models Good at Lexical Semantics? A Case of Taxonomy Learning (2024.lrec-main)

Challenge:	Existing approaches to generate toxic content by large language models are based on pipelines . current approaches focus on preserving performance while effectively mitigating toxicity .
Approach:	They propose a framework for implicit knowledge editing and controlled text generation by using hard negatives.
Outcome:	The proposed framework significantly reduces toxic generation while maintaining strong performance on downstream tasks.

Copied to clipboard

Viktor Moskvoretskii, Alexander Panchenko, Irina Nikishina

How Trustworthy are Open-Source LLMs? An Assessment under Malicious Demonstrations Shows their Vulnerabilities (2024.naacl-long)

Challenge:	Recent studies on LLMs do not pay enough attention to linguistic and lexical semantic tasks, such as taxonomy learning.
Approach:	They propose a method for stochastic graph traversal and a new algorithm for data collection . they propose LLaMA-2 and Mistral for a lexical semantic task .
Outcome:	The proposed models can perform linguistic and lexical tasks, but they lack basic skills in taxonomy learning.

Copied to clipboard

Lingbo Mo, Boshi Wang, Muhao Chen, Huan Sun

Responsible & Trustworthy NLP

Challenge:	Rapid progress in open-source Large Language Models (LLMs) is driving AI development, but lacks sufficient trustworthiness to detect and mitigate adversarial demonstrations.
Approach:	They propose an extended Chain of Utterances-based (CoU) prompting strategy to attack open-source LLMs.
Outcome:	The proposed attack strategy is based on malicious demonstrations and toxicity tests on open-source models.

MoDULA: Mixture of Domain-Specific and Universal LoRA for Multi-Task Learning (2024.emnlp-main)

Copied to clipboard

Yufei Ma, Zihan Liang, Huangyu Dai, Ben Chen, Dehong Gao, Zhuoran Ran, Wang Zihan, Linbo Jin, Wen Jiang, Guannan Zhang, Xiaoyan Cai, Libin Yang

Responsible & Trustworthy NLP

Challenge:	Recent advances in open-source Large Language Models (LLMs) have achieved notable successes in natural language processing.
Approach:	They propose a Parameter Efficient Fine-Tuning paradigm for improved fine-tuning and parameter efficiency in multi-task learning.
Outcome:	The proposed model outperforms existing methods on multi-task learning while reducing training costs by over 80% without losing general capability.

QUEST: Efficient Extreme Multi-Label Text Classification with Large Language Models on Commodity Hardware (2024.findings-emnlp)

Copied to clipboard

Chuang Zhou, Junnan Dong, Xiao Huang, Zirui Liu, Kaixiong Zhou, Zhaozhuo Xu

QuZO: Quantized Zeroth-Order Fine-Tuning for Large Language Models (2025.emnlp-main)

Challenge:	Extreme multi-label text classification (EMTC) involves predicting multiple labels from a vast pool of candidates based on a user’s textual query.
Approach:	They propose a Quantized and Efficient Learning with Sampling Technique that uses a hash sampling module to reduce the data volume to one-fourth of its original size.
Outcome:	Extensive experiments show that QUEST outperforms existing methods while requiring fewer computational resources.

Copied to clipboard

Jiajun Zhou, Yifan Yang, Kai Zhen, Ziyue Liu, Yequan Zhao, Ershad Banijamali, Athanasios Mouchtaris, Ngai Wong, Zheng Zhang

SuLoRA: Subspace Low-Rank Adaptation for Parameter-Efficient Fine-Tuning (2025.findings-acl)

Challenge:	Large Language Models (LLMs) are quantized to lower precision to reduce memory cost and latency in inference.
Approach:	They propose a quantized zeroth-order framework for fine-tuning Large Language Models (LLMs) using low-precision forward passes.
Outcome:	The proposed method achieves comparable results to first-order methods in FP8 and superior accuracy in INT8 and INT4 training.

Copied to clipboard

Chenhao Ding, Jiangyang Li, SongLin Dong, Xinyuan Gao, Yuhang He, Yihong Gong

SweetieChat: A Strategy-Enhanced Role-playing Framework for Diverse Scenarios Handling Emotional Support Agent (2025.coling-main)

Challenge:	Existing methods for fine-tuning large language models (LLMs) introduce parameter interference, leading to a gap in generalization performance for specific tasks compared to full fine-uning.
Approach:	They propose a parameter-separated low-rank adapter to account for task differences by decomposing LoRA’s parameter matrix into multiple independent subspaces and assigning them differentially to distinct tasks.
Outcome:	The proposed method outperforms LoRA in trainable parameter efficiency and overall model performance on various NLP tasks.

Copied to clipboard

Jing Ye, Lu Xiang, Yaping Zhang, Chengqing Zong

Dialogue Systems & Conversational Agents

Challenge:	Large Language Models (LLMs) have demonstrated promising potential in providing empathetic support during interactions, but their responses are often verbose or overly formulaic, failing to adequately address the diverse emotional support needs of real-world scenarios.
Approach:	They propose a strategy-enhanced role-playing framework that emulates real-world interactions and a dataset that is used to develop an emotional support agent.
Outcome:	The proposed framework emulates real-world interactions and promotes a broader range of dialogues and Emotional Support Agent training.

Take the essence and discard the dross: A Rethinking on Data Selection for Fine-Tuning Large Language Models (2025.naacl-long)

Copied to clipboard

Ziche Liu, Rui Ke, Yajiao Liu, Feng Jiang, Haizhou Li

DeepRTL2: A Versatile Model for RTL-Related Tasks (2025.findings-acl)

Challenge:	Existing studies focus on data selection but lack a clear, unified framework . variability in experimental settings complicates systematic comparisons .
Approach:	They propose a three-stage scheme to standardize data selection for fine-tuning large language models . they propose unified comparison approach that incorporates ratio-based efficiency and ranking-based feasibility metrics to address inconsistencies across experiments.
Outcome:	The proposed scheme outperforms existing methods in a dozen key studies and identifies key challenges.

Copied to clipboard

Yi Liu, Hongji Zhang, Yunhao Zhou, Zhengyuan Shi, Changran Xu, Qiang Xu

Visual–Linguistic Abductive Reasoning with LLMs for Knowledge-based Visual Question Answering (2026.findings-eacl)

Challenge:	Integration of large language models into electronic design automation has been a key driver in eDA.
Approach:	They propose a family of large language models that unifies generation- and embedding-based tasks related to RTL.
Outcome:	The proposed model achieves state-of-the-art performance across all evaluated tasks.

Copied to clipboard

Jieun Kim, Yujin Jeong, Sung-Bae Cho

Multimodality

Challenge:	Recent efforts to leverage large language models for reasoning focus on visual perception and language reasoning as separate processes.
Approach:	They propose a method that integrates visual and linguistic modalities into interpretable abductive reasoning chains.
Outcome:	The proposed method improves performance on AOKVQA, OKVQA and GQA by 2.31% . it uses fuzzy scoring to select the most coherent combination, enabling unified reasoning .

When Long Helps Short: How Context Length in Supervised Fine-tuning Affects Behavior of Large Language Models (2025.emnlp-main)

Copied to clipboard

Yingming Zheng, Hanqi Li, Kai Yu, Lu Chen

GenderAlign: An Alignment Dataset for Mitigating Gender Bias in Large Language Models (2025.acl-long)

Challenge:	Large language models (LLMs) have achieved impressive performance across NLP tasks.
Approach:	They propose to use long-context SFT to improve short-contemporary performance . they also decouple and analyze two key components, Multi-Head Attention and Feed-Forward Network .
Outcome:	The proposed model improves short-context performance, contrary to pretraining.

Copied to clipboard

Tao Zhang, Ziqian Zeng, YuxiangXiao YuxiangXiao, Huiping Zhuang, Cen Chen, James R. Foulds, Shimei Pan

GiFT: Gibbs Fine-Tuning for Code Generation (2025.acl-long)

Challenge:	Large Language Models (LLMs) generate content that exhibits gender biases, raising ethical concerns.
Approach:	They propose to use a dataset to identify gender biases in Large Language Models (LLMs) this dataset is a "chosen" and "rejected" LLM alignment is an effective approach to mitigate gender bias.
Outcome:	The proposed dataset shows that it reduces gender bias and improves quality.

Copied to clipboard

Haochen Li, Wanjin Feng, Xin Zhou, Zhiqi Shen

Programming Languages in NLP

Challenge:	Training Large Language Models (LLMs) with synthetic data is a prevalent practice in code generation.
Approach:	They propose a method to fine-tune large language models with code drawn from a conditional distribution, conditioned on a specific seed description.
Outcome:	The proposed method improves performance on four datasets and shows that it can be used to fine-tune LLMs with code derived from the marginal distribution.

Two Intermediate Translations Are Better Than One: Fine-tuning LLMs for Document-level Translation Refinement (2025.acl-long)

Copied to clipboard

Yichen Dong, Xinglin Lyu, Junhui Li, Daimeng Wei, Min Zhang, Shimin Tao, Hao Yang

Machine Translation

Challenge:	Recent research has shown that large language models (LLMs) can enhance translation quality through self-refinement.
Approach:	They propose to extend translation refinement from sentence-level to document-level by using document-to-document (Doc2Doc) translations.
Outcome:	The proposed method improves translation quality across ten translation tasks with LLaMA-3-8B-Instruct and Mistral-Nemo-Instru.

Towards Medical Complex Reasoning with LLMs through Medical Verifiable Problems (2025.findings-acl)

Copied to clipboard

Junying Chen, Zhenyang Cai, Ke Ji, Xidong Wang, Wanlong Liu, Rongsheng Wang, Benyou Wang

Reasoning

Challenge:	OpenAI o1 has been a significant milestone in large language model development . however, most research in reasoning has focused on mathematical tasks . medical domains require robust reasoning to provide reliable answers .
Approach:	They propose a method to verify medical reasoning using a medical verifier . they also propose RL and reinforcement learning to enhance reasoning .
Outcome:	The proposed method outperforms general and medical-specific baselines using only 40K verifiable problems.

HyQE: Ranking Contexts with Hypothetical Query Embeddings (2024.findings-emnlp)

Copied to clipboard

Weichao Zhou, Jiaxin Zhang, Hilaf Hasson, Anu Singh, Wenchao Li

MLAS-LoRA: Language-Aware Parameters Detection and LoRA-Based Knowledge Transfer for Multilingual Machine Translation (2025.acl-long)

Challenge:	Existing approaches to rank contexts rely on similarity between contexts and queries, but these methods are limited by the number of candidate contexts.
Approach:	They propose a scalable ranking framework that combines embedding similarity and large language models without fine-tuning.
Outcome:	The proposed framework improves the performance across multiple benchmarks.

Copied to clipboard

Tianyu Dong, Bo Li, Jinsong Liu, Shaolin Zhu, Deyi Xiong

Multilinguality

Challenge:	Large language models (LLMs) have demonstrated strong performance even with limited parallel data.
Approach:	They propose a multiple language-aware LoRA knowledge transfer framework that selectively adapts LLMs to MT by transferring knowledge from a large teacher to a small student model.
Outcome:	The proposed framework outperforms baseline models on multilingual language pairs by +1.7 BLEU on average.

Large Language Models Can Be Contextual Privacy Protection Learners (2024.emnlp-main)

Copied to clipboard

Yijia Xiao, Yiqiao Jin, Yushi Bai, Yue Wu, Xianjun Yang, Xiao Luo, Wenchao Yu, Xujiang Zhao, Yanchi Liu, Quanquan Gu, Haifeng Chen, Wei Wang, Wei Cheng

Efficient Layer-wise LLM Fine-tuning for Revision Intention Prediction (2025.findings-emnlp)

Challenge:	Large Language Models (LLMs) have demonstrated remarkable linguistic comprehension and generation capability, but when applied to specialized industries, they face challenges such as hallucination, insufficient domain knowledge, and failing to incorporate the latest domain knowledge.
Approach:	They propose a paradigm for fine-tuning LLMs that effectively injects domain-specific knowledge while safeguarding inference-time data privacy.
Outcome:	The proposed model protects private data while enhancing the model's knowledge.

Copied to clipboard

Zhexiong Liu, Diane Litman

DrAgent: Empowering Large Language Models as Medical Agents for Multi-hop Medical Reasoning (2025.findings-emnlp)

Challenge:	Large Language Models have shown extraordinary success across text generation tasks . however, their potential for simple yet essential text classification remains underexplored .
Approach:	a plug-and-play layer-wise parameter-efficient fine-tuning framework is proposed . it fine- tunes a subset of important LLM layers while freezing redundant ones .
Outcome:	a plug-and-play framework fine-tunes a subset of important LLM layers while freezing redundant layers.

Copied to clipboard

Fenglin Liu, Zheng Li, Hongjian Zhou, Qingyu Yin, Jingfeng Yang, Xin Liu, Zhengyang Wang, Xianfeng Tang, Shiyang Li, Xiang He, Ruijie Wang, Bing Yin, Xiao Gu, Lei Clifton, David A. Clifton

The Distracting Effect: Understanding Irrelevant Passages in RAG (2025.acl-long)

Challenge:	commercial LLMs can be difficult to use in real-world clinical decision-making . a lightweight LLM can be used to collaborate with diverse clinical tools .
Approach:	They propose a lightweight LLM that can be used to build medical LLMs as agents . they use recursive curriculum learning to optimize the LLM in an easy-to-hard progression .
Outcome:	The proposed approach outperforms human experts in medical examinations on diverse datasets.

Copied to clipboard

Chen Amiraz, Florin Cuconasu, Simone Filice, Zohar Karnin

Simultaneous Masking, Not Prompting Optimization: A Paradigm Shift in Fine-tuning LLMs for Simultaneous Translation (2024.emnlp-main)

Challenge:	Existing methods to detect and use hard distracting passages in RAG can cause problems . retrieved passages contain irrelevant but semantically related information that may mislead the LLM .
Approach:	They propose a method to identify and use hard distracting passages to improve RAG . they find that adding retrieved passages is found to ground the LLM response .
Outcome:	The proposed method achieves up to 7.5% increase in answering accuracy compared to fine-tuned datasets.

Copied to clipboard

Matthew Raffel, Victor Agostinelli, Lizhong Chen

Language Model Fine-Tuning on Scaled Survey Data for Predicting Distributions of Public Opinions (2025.acl-long)

Challenge:	Current fine-tuning methods to adapt LLMs for simultaneous translation suffer from several issues, such as unnecessarily expanded training sets, increased prompt sizes, or restriction to a single decision policy.
Approach:	They propose a new paradigm for fine-tuning large language models for simultaneous translation using an attention mask approach.
Outcome:	The proposed model improves translation quality compared to state-of-the-art models on five language pairs while reducing the computational cost.

Copied to clipboard

Joseph Suh, Erfan Jahanparast, Suhong Moon, Minwoo Kang, Serina Chang

On Zero-Shot Counterspeech Generation by LLMs (2024.lrec-main)

Challenge:	Prior studies have failed to accurately predict distribution of survey responses from human subjects.
Approach:	They propose to fine-tune large language models to predict human response distributions by leveraging unique structural characteristics of survey data.
Outcome:	The proposed model can capture group-specific variability in public opinions, generalizing to unseen subpopulations, survey waves and question topics, and different survey families.

Copied to clipboard

Punyajoy Saha, Aalok Agrawal, Abhik Jana, Chris Biemann, Animesh Mukherjee

GASE: Graph-Aware Semantic Embedding Learning with Frozen LLMs for Text-Attributed Graphs (2026.acl-long)

Challenge:	Large Language Models (LLMs) are used in numerous NLP tasks, including counterspeech generation.
Approach:	They propose three different prompting strategies for generating different types of counterspeech and propose a set of prompting techniques for counterspeak generation.
Outcome:	The proposed prompting strategies improve the performance of the models for counterspeech generation in two datasets, but with high toxicity with increase in model size.

Copied to clipboard

Mingqian Ding, Jianjun Li, Wenqi Yang, Zhibo Zhang, Yushen Fang

BioTool: A Comprehensive Tool-Calling Dataset for Enhancing Biomedical Capabilities of Large Language Models (2026.acl-long)

Challenge:	Large Language Models (LLMs) have shown strong potential for text-attributed graph (TAG) learning, yet effectively integrating LLM semantics with graph structural information remains challenging.
Approach:	They propose a framework for learning Graph-Aware Semantic Embeddings using frozen LLMs.
Outcome:	The proposed framework outperforms state-of-the-art methods on node classification and achieves a 5 speedup over fine-tuning-based methods.

Copied to clipboard

Xin Gao, Ruiyi Zhang, Meixi Du, Peijia Qin, Pengtao Xie