TRAINING FRAMEWORK

Keyphrase Generation with Fine-Grained Evaluation-Guided Reinforcement Learning (2021.findings-emnlp)

Challenge:	Modern industrial applications increasingly demand language models capable of multi-step reasoning and tool use in real-world settings.
Approach:	They propose a model family that trains via multi-round reinforcement learning on synthetic data and open-source data.
Outcome:	The proposed model train on synthetic and open-source data achieves strong performance on multiple agentic benchmarks and in an industrial agent system.

Copied to clipboard

Yichao Luo, Yige Xu, Jiacheng Ye, Xipeng Qiu, Qi Zhang

Structured Data in NLP

Challenge:	Existing KG evaluation metrics are only aware of the exact correctness of predictions on phrase-level and ignore semantic similarities between similar predictions and targets, which inhibits the model from learning deep linguistic patterns.
Approach:	They propose a fine-grained evaluation metric to improve the previous KG framework . the evaluation metrics are only aware of the exact correctness of predictions on phrase-level .
Outcome:	The proposed method outperforms the existing frameworks among all evaluation scores.

GenTool: Enhancing Tool Generalization in Language Models through Zero-to-One and Weak-to-Strong Simulation (2025.findings-acl)

Copied to clipboard

Jie He, Jennifer Neville, Mengting Wan, Longqi Yang, Hui Liu, Xiaofeng Xu, Xia Song, Jeff Z. Pan, Pei Zhou

Learning from Few Samples: A Novel Approach for High-Quality Malcode Generation (2025.emnlp-main)

Challenge:	Large Language Models (LLMs) can expand their capabilities by integrating external tools.
Approach:	They propose a training framework that prepares LLMs for diverse generalization challenges in tool utilization.
Outcome:	The proposed framework improves the tool-usage capabilities of LLMs by up to 8B parameters, surpassing GPT-4o.

Copied to clipboard

Haijian Ma, Daizong Liu, Xiaowen Cai, Pan Zhou, Yulai Xie

Programming Languages in NLP

Challenge:	Intrusion detection systems (IDS) are limited in labeled samples due to scarcity and lack of diversity in malicious samples.
Approach:	They propose a semi-supervised framework that integrates Generative Adversarial Networks with Large Language Models to enhance malicious code generation and SQL Injection detection capabilities.
Outcome:	The proposed framework enhances malicious code generation and detection capabilities in few-sample learning scenarios.

Controllable Summarization with Constrained Markov Decision Process (2021.tacl-1)

Copied to clipboard

Hou Pong Chan, Lu Wang, Irwin King

Multi-agent Learning for Neural Machine Translation (D19-1)

Challenge:	Existing controllable summarization models do not allow users to specify their preference for a particular attribute of the generated summaries.
Approach:	They propose a novel training framework based on Constrained Markov Decision Process (CMDP) that includes a reward function and constraints to facilitate better summarization control.
Outcome:	The proposed model can be applied to control important attributes of summarization, including length, covered entities, and abstractiveness, while complying with a given attribute’s requirement.

Copied to clipboard

Tianchi Bi, Hao Xiong, Zhongjun He, Hua Wu, Haifeng Wang

Multilinguality

Challenge:	Experimental results show that training with more than one agent improves translation quality and improves accuracy.
Approach:	They propose to introduce diverse agents in an in- teractive updating process to train NMT models with an additional agent.
Outcome:	The proposed approach improves on NIST Chinese-English, IWSLT 2014 German- English, WMT 2014 English-German translation tasks and shows competitive performance on all tasks.

ELLA: Efficient Lifelong Learning for Adapters in Large Language Models (2026.eacl-long)

Copied to clipboard

Shristi Das Biswas, Yue Zhang, Anwesan Pal, Radhika Bhargava, Kaushik Roy

Syntriever: How to Train Your Retriever with Synthetic Data from LLMs (2025.findings-naacl)

Challenge:	Existing approaches to training Large Language Models (LLMs) suffer from catastrophic forgetting when adapted sequentially to new tasks in a continual learning (CL) setting. Existing methods are impractical and could potentially violate privacy.
Approach:	They propose a training framework built on the principle of selective subspace de-correlation that characterizes the structure of past updates and penalizes alignments along their high-energy, task-specific directions.
Outcome:	The proposed training framework achieves state-of-the-art CL performance on three popular benchmarks spanning both classification and generative tasks with relative accuracy gains of up to 9.6% and a 35 smaller memory footprint.

Copied to clipboard

Minsang Kim, Seung Jun Baek

Information Retrieval

Challenge:	Large Language Models (LLMs) have become a core technology in various NLP applications such as chatbots and coding assistants.
Approach:	They propose a training framework for retrievers using synthetic data from black-box LLMs.
Outcome:	The proposed training framework achieves state-of-the-art on benchmark datasets from various domains in nDCG@K.

Training Language Models to Generate Text with Citations via Fine-grained Rewards (2024.acl-long)

Copied to clipboard

Chengyu Huang, Zeqiu Wu, Yushi Hu, Wenya Wang

RIVAL: Reinforcement Learning with Iterative and Adversarial Optimization for Machine Translation (2025.findings-emnlp)

Challenge:	Recent Large Language Models (LLMs) are prone to hallucination and their outputs often contain incorrect or unverifiable claims.
Approach:	They propose a training framework using fine-grained rewards to teach LLMs to generate highly supportive and relevant citations while ensuring the correctness of their responses.
Outcome:	The proposed training framework outperforms existing methods on QA datasets and surpasses GPT-3.5-turbo on LLaMA-2-7B.

Copied to clipboard

Tianjiao Li, Mengran Yu, Chenyu Shi, Yanjun Zhao, Xiaojing Liu, Qi Zhang, Xuanjing Huang, Qiang Zhang, Jiayin Wang

FC-TTS: Style and Timbre Control in Zero-Shot Text-to-Speech with Disentangled Speech Representations (2026.acl-long)

Challenge:	Using reinforcement learning from human feedback, large language models perform poorly when applied to colloquial subtitle translation tasks.
Approach:	They propose an adversarial training framework that iteratively updates the offline reward model and the online LLM to improve training outcomes.
Outcome:	The proposed training framework significantly improves upon translation baselines.

Copied to clipboard

Yoonhyung Lee, Hyunsin Park, Jinhwan Park, Jinkyu Lee

ModularMoE: Fast LLM Customization with Parameter-Sharing Mixture-of-Experts for Low-Resource Settings (2026.findings-acl)

Challenge:	Recent advances in text-to-speech (TTS) have enabled accurate imitation of reference speech in terms of both speaking style and speaker timbre.
Approach:	They propose a zero-shot text-to-speech framework that enables disentangled control of style and timbre by conditioning on two distinct reference utterances.
Outcome:	The proposed framework achieves high-fidelity synthesis and competitive zero-shot naturalness while supporting consistent and independent manipulation of style and timbre.

Copied to clipboard

Jiaxing Liu, Qi Qi, Haifeng Sun, Dunjun Li, Zirui Zhuang, Bo He, Xiang Yang, Cong Liu, Jianxin Liao, Jingyu Wang

Responsible & Trustworthy NLP

Challenge:	Large Language Models impose significant computational and storage burdens on personal devices . existing customization approaches incur excessive computational costs or lead to suboptimal performance .
Approach:	They propose a training framework that converts pre-trained LLMs into parameter-sharing MoE models for lightweight deployment.
Outcome:	The proposed training framework outperforms state-of-the-art training frameworks at the same sparsity level while delivering up to 2.71 inference speedup.

Memory Dial: A Training Framework for Controllable Memorization in Language Models (2026.findings-acl)

Copied to clipboard

Xiangbo Zhang, Ali Emami

Exploring Better Text Image Translation with Multimodal Codebook (2023.acl-long)

Challenge:	Existing approaches to memorization detection are post-hoc . large language models can reproduce training data verbatim, complicating accuracy estimates .
Approach:	They propose a training framework that makes memorization an explicit variable.
Outcome:	The proposed framework produces models identical in architecture, data, and optimization, but varying in memorization pressure.

Copied to clipboard

Zhibin Lan, Jiawei Yu, Xiang Li, Wen Zhang, Jian Luan, Bin Wang, Degen Huang, Jinsong Su

Multimodality

Challenge:	Current studies on text image translation face bottlenecks due to lack of a publicly available dataset and poor optical character recognition.
Approach:	They propose a text image translation model with a multimodal codebook and an OCR dataset for Chinese-English translation.
Outcome:	The proposed model can associate the image with relevant texts, providing useful supplementary information for translation.

Towards Higher Pareto Frontier in Multilingual Machine Translation (2023.acl-long)

Copied to clipboard

Yichong Huang, Xiaocheng Feng, Xinwei Geng, Baohang Li, Bing Qin

Multilinguality

Challenge:	Existing Pareto optimization approaches are limited by the long-tailed distribution of multilingual corpora.
Approach:	They propose a Pareto mutual distillation framework that pushes the Paret frontier outwards rather than making trade-offs.
Outcome:	The proposed framework pushes the Pareto frontier outwards rather than making trade-offs, the authors show.

CycleOIE: A Low-Resource Training Framework For Open Information Extraction (2025.coling-main)

Copied to clipboard

Zhihong Jin, Chunhong Zhang, Zheng Hu, Jibin Yu, Ruiqi Ma, Qingyun Chen, Xiaohao Liao, Yanxing Zhang

Information Extraction & Text Mining

Challenge:	Open Information Extraction (OpenIE) models rely heavily on large amounts of annotated data.
Approach:	They propose a training framework that maximizes data efficiency through a cycle-consistency mechanism.
Outcome:	The proposed approach improves the quality of training data by curating low-quality datasets annotated by a large language model.

Co-Evolving LLMs and Embedding Models via Density-Guided Preference Optimization for Text Clustering (2025.emnlp-main)

Copied to clipboard

Zetong Li, Qinliang Su, Minhua Huang, Yin Yang

Incentivizing Parametric Knowledge via Reinforcement Learning with Verifiable Rewards for Cross-Cultural Entity Translation (2026.acl-long)

Challenge:	Existing methods for text clustering use static pseudo-oracles, i.e., unidirectionally querying them for similarity assessment or data augmentation.
Approach:	They propose a training framework that enables bidirectional refinement between LLMs and embedding models by using task-aware prompts to guide the LLM in generating interpretations for the input texts.
Outcome:	Experiments on 14 benchmark datasets across 5 tasks demonstrate the effectiveness of the proposed training framework.

Copied to clipboard

Jiang Zhou, Xiaohu Zhao, Xinwei Wu, Tianyu Dong, Hao Wang, Yangyang Liu, Heng Liu, Linlong Xu, Longyue Wang, Weihua Luo, Deyi Xiong

Machine Translation

Challenge:	Current systems often fall short of this goal in settings where translation hinges on culturally grounded entities such as books, films, places, songs and idioms.
Approach:	They propose a framework that anchors supervision on a verifiable, entity-level reward signal and incorporates lightweight structural gates to stabilize optimization.
Outcome:	The proposed framework improves on XC-Translate and shows that it can learn a robust reasoning process rather than imitating reference translations.

Judge and Improve: Towards a Better Reasoning of Knowledge Graphs with Large Language Models (2025.emnlp-main)

Copied to clipboard

Mo Zhiqiang, Yang Hua, Jiahui Li, Yuan Liu, Shawn Wong, Jianmin Huang

GeoLAN: Geometric Learning of Latent Explanatory Directions in Large Language Models (2026.findings-acl)

Challenge:	Existing approaches to integrating graph and language models face two key limitations: achieving robust semantic alignment and ensuring interpretability in outputs.
Approach:	They propose a framework to integrate graph and language modalities while enhancing transparency.
Outcome:	Extensive experiments on three benchmark datasets show that the proposed framework surpasses existing methods in efficiency and generates outputs that are significantly more interpretable.

Copied to clipboard

Tianyu Pan, Damon L. Woodard

Personalized Federated Learning for Text Classification with Gradient-Free Prompt Tuning (2024.findings-naacl)

Challenge:	Large language models lack transparency and are often unable to explain causal relationships .
Approach:	They propose a training framework that treats token representations as geometric trajectories and applies stickiness conditions to the Kakeya Conjecture.
Outcome:	The proposed training framework maintains task accuracy while improving geometric metrics and reducing fairness biases.

Copied to clipboard

Rui Wang, Tong Yu, Ruiyi Zhang, Sungchul Kim, Ryan Rossi, Handong Zhao, Junda Wu, Subrata Mitra, Lina Yao, Ricardo Henao

ET-Agent: Incentivizing Effective Tool-Integrated Reasoning Agent via Behavior Calibration (2026.acl-long)

Challenge:	Pretrained language models (PLMs) are used for personalized federated learning . communication costs are high with large PLMs, and local training is expensive .
Approach:	They propose a framework for federated learning with pretrained language models . they propose 'discrete local search' and compression mechanism for local training .
Outcome:	The proposed framework achieves superior performance compared with baselines.

Copied to clipboard

Yifei Chen, Guanting Dong, Zhicheng Dou

SaySelf: Teaching LLMs to Express Confidence with Self-Reflective Rationales (2024.emnlp-main)

Challenge:	Existing training frameworks for Large Language Models (LLMs) focus on answers’ accuracy, overlooking specific alignment for behavior patterns.
Approach:	They propose a training framework for calibrating agent’s tool-use behavior through two synergistic perspectives: self-evolving data flywheel and behavior calibration training.
Outcome:	The proposed framework improves the accuracy, efficiency, reasoning conciseness, and tool execution accuracy of large language models.

Copied to clipboard

Tianyang Xu, Shujin Wu, Shizhe Diao, Xiaoze Liu, Xingyao Wang, Yangyi Chen, Jing Gao

Benchmarking and Improving Compositional Generalization of Multi-aspect Controllable Text Generation (2024.acl-long)

Challenge:	Existing approaches to elicit confidence from large language models are limited to binary or inaccurate group-level confidence estimates.
Approach:	They propose a training framework that teaches LLMs to express more fine-grained confidence estimates.
Outcome:	The proposed training framework reduces the confidence calibration error and maintains the performance of the model.

Copied to clipboard

Tianqi Zhong, Zhaoyi Li, Quan Wang, Linqi Song, Ying Wei, Defu Lian, Zhendong Mao

SURE: Safety Understanding and Reasoning Enhancement for Multimodal Large Language Models (2025.emnlp-main)

Challenge:	Existing MCTG methods face a noticeable performance drop in compositional testing.
Approach:	They propose a benchmark to evaluate compositional generalization of MCTG methods by combining multi-aspect labeled datasets and a crafted three-dimensional evaluation protocol.
Outcome:	The proposed framework improves compositional generalization performance by 3.64% and 94.4% in compositional testing.

Copied to clipboard

Yuxin Gou, Xiaoning Dong, Qin Li, Shishen Gu, Richang Hong, Wenbo Hu

Profanity-Avoiding Training Framework for Seq2seq Models with Certified Robustness (2021.emnlp-main)

Challenge:	Existing multimodal large language models incorporate visual and textual information, but introduces new and complex safety risks.
Approach:	They propose a safety reasoning framework that integrates visual modalities into multimodal models to help them resist jailbreak attacks.
Outcome:	The proposed framework improves model safety while avoiding over-defense . it is based on a large-scale safety reasoning dataset .

Copied to clipboard

Hengtong Zhang, Tianhang Zheng, Yaliang Li, Jing Gao, Lu Su, Bo Li

Robustness in NLP

Challenge:	a recent study shows that inappropriate language can cause models to output profanity . authors propose a training framework to prevent such outputs from hurting the usability of models .
Approach:	proposed training framework eliminates the causes that trigger the generation of profanity . authors propose a framework that leverages a short list of profans to prevent this .
Outcome:	a proposed training framework can prevent models from generating profanity . the proposed framework leverages a short list of profanities examples .

R2D2: Robust Data-to-Text with Replacement Detection (2022.emnlp-main)

Copied to clipboard

Linyong Nan, Lorenzo Jaime Flores, Yilun Zhao, Yixin Liu, Luke Benson, Weijin Zou, Dragomir Radev

Syntactically Robust Training on Partially-Observed Data for Open Information Extraction (2022.findings-emnlp)

Challenge:	Existing methods to mitigate unfaithful text generation are inadequate . data-to-text generation requires a structured input format .
Approach:	They propose a training framework that addresses unfaithful Data-to-Text generation by training a system as a generator and faithfulness discriminator with additional replacement detection and unlikelihood learning tasks.
Outcome:	The proposed training framework improves FeTaQA, LogicNLG, and ToTTo fidelity on D2T systems.

Copied to clipboard

Ji Qi, Yuxiang Chen, Lei Hou, Juanzi Li, Bin Xu

Information Extraction & Text Mining

Challenge:	Open Information Extraction models have shown promising results with sufficient supervision, but the syntactic distribution of training data is partially observable in comparison to the real world.
Approach:	They propose a syntactically robust training framework that enables models to be trained on a multi-paraphrase distribution based on diverse paraphrase generation.
Outcome:	The proposed framework can be applied to other syntactic partial observable domains.

M-LongDoc: A Benchmark For Multimodal Super-Long Document Understanding And A Retrieval-Aware Tuning Framework (2025.emnlp-main)

Copied to clipboard

Yew Ken Chia, Liying Cheng, Hou Pong Chan, Maojia Song, Chaoqun Liu, Mahani Aljunied, Soujanya Poria, Lidong Bing

Information Retrieval

Challenge:	Existing benchmarks for large multimodal models focus on short documents with less than 50 pages and are limited to extraction-based questions.
Approach:	They propose a retrieval-aware tuning approach to improve the accuracy of multimodal document reading by 4.6%.
Outcome:	The proposed framework improves the accuracy of model responses by 4.6% compared to existing benchmarks on documents with hundreds of pages and longer documents with more complex content.

From Past To Path: Masked History Learning for Next-Item Prediction in Generative Recommendation (2026.acl-long)

Copied to clipboard

Kaiwen Wei, Kejun he, Xiaomian Kang, Jie Zhang, null Ymyang, Li Jin, Zhenyang Li, Jiang Zhong, Richard He Bai, Junnan Zhu

Overcoming Language Priors in Visual Question Answering via Distinguishing Superficially Similar Instances (2022.coling-1)

Challenge:	Generative recommendation models inherently bias towards local contexts, failing to capture deeper historical dependencies necessary for understanding complex user intents.
Approach:	They propose a training framework that shifts the objective from simple next-step prediction to deep comprehension of history by entropy-guided masking policy and a curriculum learning scheduler to enhance the framework.
Outcome:	The proposed framework outperforms state-of-the-art generative models on three public datasets and shows that it is more accurate than current models.

Copied to clipboard

Yike Wu, Yu Zhao, Shiwan Zhao, Ying Zhang, Xiaojie Yuan, Guoqing Zhao, Ning Jiang

Visual Data in NLP

Challenge:	Existing VQA models rely on the superficial correlation between question type and frequent answers to make predictions, without really understanding the input.
Approach:	They propose a training framework that explicitly encourages the VQA model to distinguish between superficially similar instances.
Outcome:	The proposed framework achieves state-of-the-art performance on VQA-CP v2 . it explicitly encourages the model to distinguish between the superficially similar instances .

Coordination Generation via Synchronized Text-Infilling (2022.coling-1)

Copied to clipboard

Hiroki Teranishi, Yuji Matsumoto

A Contrastive Cross-Channel Data Augmentation Framework for Aspect-Based Sentiment Analysis (2022.coling-1)

Challenge:	Generating synthetic data from pre-trained language models has enhanced performance across several NLP tasks.
Approach:	They propose a method for generating sentences with a coordinate structure in which the boundaries of its conjuncts are explicitly specified.
Outcome:	The proposed method produces promising coordination instances that provide gains for the task in low-resource settings.

Copied to clipboard

Bing Wang, Liang Ding, Qihuang Zhong, Ximing Li, Dacheng Tao

Sentiment Analysis

Challenge:	Aspect-based sentiment analysis is sensitive to multi-aspect challenges, resulting in multiple aspects in a sentence.
Approach:	They propose a framework that leverages an in-domain generator to construct more multi-aspect samples . they then boost the robustness of ABSA models via contrastive learning on these generated samples ."
Outcome:	The proposed framework outperforms baselines without any augmentations on accuracy and Macro- F1 . the proposed framework can generate more multi-aspect samples and boost the robustness of ABSA models .

ReAlign: Structured Revision for Small Language Model Alignment (2025.findings-emnlp)

Copied to clipboard

Ruijun Chen, Jiajian Guo, Hongzhan Chen, Fanqi Wan, Qifan Wang, Xiaojun Quan

Adversary-Aware DPO: Enhancing Safety Alignment in Vision Language Models via Adversarial Training (2025.findings-emnlp)

Challenge:	weak policies struggle to generate informative on-policy samples and suffer from unstable gradients when trained on off-police signals from stronger models.
Approach:	They propose a training framework that combines stability of on-policy learning with reviser-assisted supervision.
Outcome:	The proposed training framework outperforms strong preference optimization baselines on AlpacaEval-2 and Arena-Hard.

Copied to clipboard

Fenghua Weng, Jian Lou, Jun Feng, Minlie Huang, Wenjie Wang

Robustness in NLP

Challenge:	Adversary-aware DPO (ADPO) is a training framework that explicitly considers adversary.
Approach:	a new framework integrates adversarial training into a pre-trained large language model to enhance safety alignment . adversary-aware DPO provides a framework that explicitly considers adversary .
Outcome:	a new training framework outperforms baselines in safety alignment and general utility of large language models.

Improving the Robustness of Large Language Models via Consistency Alignment (2024.lrec-main)

Copied to clipboard

Yukun Zhao, Lingyong Yan, Weiwei Sun, Guoliang Xing, Shuaiqiang Wang, Chong Meng, Zhicong Cheng, Zhaochun Ren, Dawei Yin

What Do LLMs Learn First? Asymmetric Learning Dynamics of Input Complexity and Output Ambiguity in Preference Alignment (2026.acl-long)

Challenge:	Large language models have shown tremendous success in following user instructions and generating helpful responses, but their robustness is still far from optimal.
Approach:	They propose a two-stage training framework that helps a model generalize on following instructions via similar instruction augmentations.
Outcome:	The proposed training framework improves diversity and aligns the model with human expectations by differentiating subtle differences in similar responses.

Copied to clipboard

Mengyang Li, Jingwen Wang, Pinlong Zhao

Challenge:	Existing methods treat all preference pairs uniformly during training.
Approach:	They propose a training framework that maintains separate, adaptive pacing schedules for each dimension.
Outcome:	The proposed training framework outperforms curriculum baselines by 2.1% and 0.21 points . it achieves 42.3% length-controlled win rate on AlpacaEval 2.0 and 7.66 on MT-Bench .

ViStruct: Visual Structural Knowledge Extraction via Curriculum Guided Code-Vision Representation (2023.emnlp-main)

Copied to clipboard

Yangyi Chen, Xingyao Wang, Manling Li, Derek Hoiem, Heng Ji

Multimodality

Challenge:	State-of-the-art vision-language models have limited performance in structural knowledge extraction, such as relations between objects.
Approach:	They propose to leverage the inherent structure of programming language to depict visual structural information in a well-organized structured format.
Outcome:	The proposed framework improves visual structural knowledge extraction on visual structure prediction tasks.

Learning Fine-Grained Grounded Citations for Attributed Large Language Models (2024.findings-acl)

Copied to clipboard

Lei Huang, Xiaocheng Feng, Weitao Ma, Yuxuan Gu, Weihong Zhong, Xiachong Feng, Weijiang Yu, Weihua Peng, Duyu Tang, Dandan Tu, Bing Qin

FastDiSS: Few-step Match Many-step Diffusion Language Model on Sequence-to-Sequence Generation (2026.findings-acl)

Challenge:	despite impressive performance, large language models still struggle with hallucinations . current approaches suffer from suboptimal citation quality due to reliance on in-context learning .
Approach:	They propose a framework that teaches large language models to generate fine-grained citations.
Outcome:	The proposed framework outperforms all baselines on the ALCE benchmark and achieves an average improvement of 14.21% in citation quality.

Copied to clipboard

Dat Nguyen Cong, Tung Kieu, Hoang Thanh-Tung

HAF-RM: A Hybrid Alignment Framework for Reward Model Training (2025.acl-long)

Challenge:	Existing models that correct errors in the model but lack a high quality of output . a novel training framework that matches inference noise to the model's inference signal improves performance .
Approach:	They propose a training framework that matches inference noise to model errors by perturbing the self-conditioning signal to match inference errors.
Outcome:	The proposed framework surpasses standard continuous diffusion models while providing 400x faster inference speed.

Copied to clipboard

Shujun Liu, Xiaoyu Shen, Yuhang Lai, Siyuan Wang, Shengbin Yue, Zengfeng Huang, Xuanjing Huang, Zhongyu Wei

SDAR: A Synergistic Diffusion-AutoRegression Paradigm for Scalable Sequence Generation (2026.findings-acl)

Challenge:	Recent studies have focused on enhancing reward models through data improvements, following the conventional training framework for reward models that directly optimizes the predicted rewards.
Approach:	They propose a hybrid alignment framework HAF-RM that incorporates additional constraint on token-level policy probabilities in addition to the reward score.
Outcome:	The proposed framework can supervise the internal preference model at the token level and optimize the mapping layer of the reward model at sequence level.

Copied to clipboard

Shuang Cheng, Yihan Bian, Dawei Liu, Yuhua Jiang, Yihao Liu, Linfeng Zhang, Qian Yao, Zhongbo Tian, Wenhai Wang, Qipeng Guo, Kai Chen, Biqing Qi, Bowen Zhou

GOAT: A Training Framework for Goal-Oriented Agent with Tools (2026.findings-acl)

Challenge:	Autoregressive (AR) language models are a dominant paradigm in the field of parallelism and non-causal modeling.
Approach:	They propose a blockwise discrete diffusion model that preserves AR-compatible serving while enabling parallel intra-block generation.
Outcome:	The proposed model achieves theoretical speedups over 5 and wall-clock speedup of 2.3 on H200 GPUs in latency-critical regimes.

Copied to clipboard

Hyunji Min, Sangwon Jung, Junyoung Sung, Dosung Lee, Leekyeung Han, Paul Hongsuck Seo

Think Before you Write: QA-Guided Reasoning for Character Descriptions in Books (2026.findings-acl)

Challenge:	Recent advances in large language models have led to remarkable progress across a wide range of natural language processing tasks.
Approach:	They propose a training framework that enables fine-tuning LLM agents without human annotation.
Outcome:	The proposed framework enables fine-tuning LLM agents without human annotation.

Copied to clipboard

Argyrios Papoudakis, Mirella Lapata, Frank Keller

Jianzhu Bao, Haozhen Zhang, Kuicai Dong, Bozhi Wu, Sarthak Ketanbhai Modi, Zi Pong Lim, Yon Shin Teo, Wenya Wang

Challenge:	Character description generation is an important capability for narrative-focused applications . however, generating accurate character descriptions from long-form narratives is challenging . enabling built-in reasoning mode of current LLMs often degrades performance .
Approach:	They propose a framework that decouples reasoning from generation by generating a structured QA reasoning trace and a generation model that conditions on this trace to produce the final character description.
Outcome:	The proposed framework improves faithfulness, informativeness, and grounding over long-context baselines.

Copied to clipboard

Multimodality

Challenge:	Chart understanding is a critical capability for vision-language models, serving as a cornerstone for automated data analysis, document understanding, and scientific research.
Approach:	They propose a chart-efficient training framework to enhance counterfactual sensitivity by code modification and a similarity-based data selection strategy.
Outcome:	The proposed framework achieves superior or comparable performance to strong chart-specific VLMs while using significantly less training data.

SMEC:Rethinking Matryoshka Representation Learning for Retrieval Embedding Compression (2025.emnlp-main)

Copied to clipboard

Biao Zhang, Lixin Chen, Tong Liu, Bo Zheng

ERRV: Eliciting Efficient Reasoning through Reasoning Vectors for Policy Optimization in Large Language Models (2026.findings-acl)

Challenge:	Large language models generate high-dimensional embeddings that capture rich semantic and syntactic information.
Approach:	They propose a training framework to reduce dimensionality and complexity of large language models.
Outcome:	Experiments on image, text, and multimodal datasets show that the proposed training framework reduces dimensionality while maintaining performance.

Copied to clipboard

Zhuowen Han, Lei Yang, Renren Jin, Dan Shi, Chenxi Sun, Deyi Xiong

DRAMA: Diverse Augmentation from Large Language Models to Smaller Dense Retrievers (2025.acl-long)

Challenge:	Existing efforts to improve reasoning efficiency of large language models focus on modifying the reinforcement learning reward, such as adding length penalties.
Approach:	They propose a training framework that elicits efficient reasoning through reasoning vectors and a framework that allows the model to generate high-quality responses during reinforcement learning.
Outcome:	The proposed framework reduces reasoning length by 30% while maintaining stability, while retaining high accuracy.

Copied to clipboard

Xueguang Ma, Xi Victoria Lin, Barlas Oguz, Jimmy Lin, Wen-tau Yih, Xilun Chen

WSDPO: A Generative Word Sense Disambiguation Framework with Chain-of-Thought and Preference Optimization (2026.acl-long)

Challenge:	Large language models (LLMs) have shown strong effectiveness and robustness when fine-tuned as dense retrievers.
Approach:	They propose a training framework that leverages pruned LLMs to train smaller generalizable dense retrievers.
Outcome:	The proposed training framework offers better multilingual and long-context capabilities than traditional encoder-based retrievers and achieves strong performance across multiple tasks and languages.

Copied to clipboard

Kunpeng Kang, Shuaimin Li, Kaiyuan Zhang, Luyang Zhang, Jiasheng Si, Bing Xu, Kehai Chen, Muyun Yang, Wenpeng Lu

Long-Context Reasoning Through Proxy-Based Chain-of-Thought Tuning (2026.acl-long)

Challenge:	Word sense disambiguation (WSD) is a fundamental task in natural language processing.
Approach:	They propose a training framework for generative WSD with chain-of-thought (CoT) and preference optimization.
Outcome:	The proposed framework achieves significant performance gains on rare and unseen settings and exhibits strong generalization in standard evaluation settings.

Copied to clipboard

Miao Li, Irina Saparina, Alexander Gurung, Mirella Lapata