DECODING PROCESS

Joint Aspect Extraction and Sentiment Analysis with Directional Graph Convolutional Networks (2020.coling-main)

Challenge:	Existing approaches to complex and cross-domain Text-to-SQL generation lack domain knowledge . domain knowledge is not incorporated to enhance their ability to generalise to unseen databases.
Approach:	They propose a framework called G3R for complex and cross-domain Text-to-SQL generation . they propose re-ranking SQL queries based on domain knowledge and a graph-guided SQL generator .
Outcome:	The proposed framework achieves state-of-the-art results on the Spider and Spider-DK benchmarks.

Copied to clipboard

Guimin Chen, Yuanhe Tian, Yan Song

Sentiment Analysis

Challenge:	End-to-end aspect-based sentiment analysis uses two sub-tasks to extract aspect terms . experimental results demonstrate the effectiveness of our approach on all datasets .
Approach:	They propose to combine aspect extraction and sentiment analysis with encoding syntactic information to improve model's representation of input sentences.
Outcome:	The proposed approach achieves state-of-the-art on three benchmark datasets.

Improving Image Captioning via Predicting Structured Concepts (2023.emnlp-main)

Copied to clipboard

Ting Wang, Weidong Chen, Yuanhe Tian, Yan Song, Zhendong Mao

Guiding Zero-Shot Paraphrase Generation with Fine-Grained Control Tokens (2023.starsem-1)

Challenge:	Existing studies on image captioning ignore the relationship between concepts . current methods for image caption generation ignore this relationship .
Approach:	They propose a structured concept predictor to predict concepts and their structures . they integrate these predictions into captioning to enhance visual signals .
Outcome:	The proposed approach improves image captioning performance by using semantic concepts as a bridge between images and texts.

Copied to clipboard

Teemu Vahtola, Mathias Creutz, Jrg Tiedemann

Entity-Aware Abstractive Multi-Document Summarization (2021.findings-acl)

Challenge:	Sequence-to-sequence paraphrase generation models struggle with the generation of diverse paraphrases.
Approach:	They propose a translation-based guided paraphrase generation model that learns useful features for promoting surface form variation in generated paraphrases from cross-lingual parallel data.
Outcome:	The proposed model learns useful features for promoting surface form variation in generated paraphrases from cross-lingual parallel data.

Copied to clipboard

Hao Zhou, Weidong Ren, Gongshen Liu, Bo Su, Wei Lu

Summarization

Challenge:	Existing models for multidocument summarization do not focus on explicitly modeling the underlying semantic information across documents.
Approach:	They propose an entityaware model for abstractive multi-document summarization that augments the classical Transformer-based encoder-decoder framework with a heterogeneous graph consisting of text units and entities as nodes.
Outcome:	The proposed model can deal with saliency and redundancy issues explicitly and can be used with pre-trained language models, arriving at improved performance.

Checkpoint Reranking: An Approach to Select Better Hypothesis for Neural Machine Translation Systems (2020.acl-srw)

Copied to clipboard

Vinay Pandramish, Dipti Misra Sharma

Improving Abstractive Dialogue Summarization with Graph Structures and Topic Words (2020.coling-main)

Challenge:	Neural Machine Translation (NMT) has produced excellent results in the field of machine translation due to generation of high-quality translations for different language pairs.
Approach:	They propose a method of re-ranking the outputs of Neural Machine Translation systems by focusing on the decoder's ability to generate distinct tokens and without the use of any language model or data.
Outcome:	The proposed method achieves translation improvement up to +0.16 BLEU points over baseline.

Copied to clipboard

Lulu Zhao, Weiran Xu, Jun Guo

Discourse Representation Structure Parsing (P18-1)

Challenge:	Existing approaches to summarize textual information are hard to capture long-distance relationships.
Approach:	They propose a Topic-word Guided Dialogue Graph Attention network to model the dialogue as an interaction graph according to topic word information.
Outcome:	The proposed model outperforms baseline models on two corpus corpus models.

Copied to clipboard

Jiangming Liu, Shay B. Cohen, Mirella Lapata

Extracting Relational Facts by an End-to-End Neural Model with Copy Mechanism (P18-1)

Challenge:	Existing semantic parsers are data-driven using annotated examples consisting of utterances and their meaning representations.
Approach:	They propose a method which transforms Discourse Representation Structures (DRSs) to trees and develop a structure-aware model which decomposes the decoding process into three stages.
Outcome:	The proposed model outperforms baseline models on the Groningen Meaning Bank (GMB) by a wide margin.

Copied to clipboard

Xiangrong Zeng, Daojian Zeng, Shizhu He, Kang Liu, Jun Zhao

A Distance-Aware Multi-Task Framework for Conversational Discourse Parsing (2022.coling-1)

Challenge:	Existing methods focus on normal class and fail to extract relational triplets precisely.
Approach:	They propose an end-to-end model which can jointly extract relational triplets from sentences . they employ two different strategies in decoding process: employing only one united decoder or applying multiple separated decodeurs.
Outcome:	The proposed model outperforms the baseline method significantly in two datasets.

Copied to clipboard

Yaxin Fan, Peifeng Li, Fang Kong, Qiaoming Zhu

Giving the Old a Fresh Spin: Quality Estimation-Assisted Constrained Decoding for Automatic Post-Editing (2025.naacl-short)

Challenge:	Existing studies have focused on graph-based and transition-based discourse parsing, but no study has investigated the advantages of both paradigms for conversational discourse paring.
Approach:	They propose a distance-aware multi-task framework that incorporates the strengths of transition-based paradigms to facilitate conversational discourse parsing.
Outcome:	The proposed framework improves the graph-based paradigm on long-distance dependency links.

Copied to clipboard

Sourabh Deoghare, Diptesh Kanojia, Pushpak Bhattacharyya

Multilinguality

Challenge:	Existing methods to improve automatic post-editing (APE) systems struggle with over-correction, despite the principle of minimal editing.
Approach:	They propose a method that incorporates word-level Quality Estimation (QE) information during the decoding process.
Outcome:	The proposed method improves on English-German, English-Hindi, and English-Marathi language pairs, with TER gains of 0.65, 1.86, and 1.44 points, respectively.

Diffusion-NAT: Self-Prompting Discrete Diffusion for Non-Autoregressive Text Generation (2024.eacl-long)

Copied to clipboard

Kun Zhou, Yifan Li, Xin Zhao, Ji-Rong Wen

Universal Dependency Parsing for Hindi-English Code-Switching (N18-1)

Challenge:	Existing non-autoregressive (NAR) text-to-text generation methods are unable to generate coherent and fluent texts due to discrete nature of text.
Approach:	They propose to integrate discrete diffusion models (DDM) into NAR text-to-text generation and integrate BART to improve the performance.
Outcome:	The proposed method outperforms competing methods and surpasses autoregressive methods on 7 datasets.

Copied to clipboard

Irshad Bhat, Riyaz A. Bhat, Manish Shrivastava, Dipti Sharma

Syntactic Text Processing

Challenge:	Code-switching data often need additional processes such as language identification, normalization and/or back-transliteration to be processed.
Approach:	They propose a neural stacking model that leverages part-of-speech tags and syntactic tree annotations in tweets to parse code-switching data.
Outcome:	The proposed model is 1.5% better than the augmented model and 3.8% better than one which uses first-best normalization and/or back-transliteration.

TTD-SQL: Tree-Guided Token Decoding for Efficient and Schema-Aware SQL Generation (2025.emnlp-industry)

Copied to clipboard

Chetan Sharma, Ramasuri Narayanam, Soumyabrata Pal, Kalidas Yeturu, Shiv Kumar Saini, Koyel Mukherjee

Programming Languages in NLP

Challenge:	Large language models (LLMs) have achieved state-of-the-art accuracy on benchmarks like Spider and BIRD, but inference latency due to sequential autoregressive decoding remains a challenge for real-time deployments.
Approach:	a new framework integrates SQL grammar and database schema constraints into the decoding process . tree-Guided Token Decoding (TTD-SQL) precomputes token-level decision trees over SQL keywords, table names, and column identifiers .
Outcome:	a new framework reduces schema hallucinations and inference latency due to autoregressive decoding . tree-Guided Token Decoding achieves 19.96% token-rate speedups .

Gaussian Process Optimization for Adaptable Multi-Objective Text Generation using Linearly-Weighted Language Models (2024.findings-naacl)

Copied to clipboard

Mohammad Mahdi Abdollah Pour, Ali Pesaranghader, Eldan Cohen, Scott Sanner

TRUE-UIE: Two Universal Relations Unify Information Extraction Tasks (2024.naacl-long)

Challenge:	Multi-objective text generation requires a method to optimize for dynamic requirements of the overall objective.
Approach:	They propose a linear combination of objective-specific language models to efficiently adapt the decoding process and optimize for the desired overall objective without retraining one or more language models.
Outcome:	The proposed method outperforms other weighting schemes and standard baselines in a few iterations of decoding.

Copied to clipboard

Yucheng Wang, Bowen Yu, Yilin Liu, Shudong Lu

Information Extraction & Text Mining

Challenge:	Information extraction (IE) tasks have a variety of schemas and objectives that differ across tasks.
Approach:	They propose a paradigm where all IE tasks are aligned to learn the same goals . they use two universal relations to extract mention spans and type recognition .
Outcome:	The proposed model achieves state-of-the-art on established benchmarks spanning 16 datasets, spanning 7 diverse IE tasks.

TSDG: Content-aware Neural Response Generation with Two-stage Decoding Process (2020.findings-emnlp)

Copied to clipboard

Junsheng Kong, Zhicheng Zhong, Yi Cai, Xin Wu, Da Ren

Give the Truth: Incorporate Semantic Slot into Abstractive Dialogue Summarization (2021.findings-emnlp)

Challenge:	Empirical results show that generative models often use a single decoder to generate a complete response at a stroke.
Approach:	They propose a content-aware model with two-stage decoding process to separate content words from function words.
Outcome:	The proposed model outperforms competing models in automatic and human evaluation on two datasets.

Copied to clipboard

Lulu Zhao, Weihao Zeng, Weiran Xu, Jun Guo

Dialogue Systems & Conversational Agents

Challenge:	Abstractive dialogue summarization suffers from a lot of factual errors due to scattered salient elements in multi-speaker information interaction process.
Approach:	They propose a slot-driven beam search algorithm to give priority to generating salient elements in a limited length by "filling-in-the-blanks".
Outcome:	The proposed algorithm improves the slot-driven beam search algorithm on different types of factual errors and human evaluation further verifies the results.

Informed Sampling for Diversity in Concept-to-Text NLG (2021.findings-emnlp)

Copied to clipboard

Giulio Zhou, Gerasimos Lampouras

Guiding the Flowing of Semantics: Interpretable Video Captioning via POS Tag (D19-1)

Challenge:	Existing methods to encourage lexical diversity for language generation tasks produce repetitive outputs, but this often comes at a cost to the perceived fluency and adequacy of the output.
Approach:	They propose to augment the decoding process with a meta-classifier trained to distinguish which words at any given timestep will lead to high-quality output.
Outcome:	The proposed method achieves a high level of diversity with minimal effect on the output’s fluency and adequacy.

Copied to clipboard

Xinyu Xiao, Lingfeng Wang, Bin Fan, Shinming Xiang, Chunhong Pan

Heterogeneous Graph Neural Networks for Keyphrase Generation (2021.emnlp-main)

Challenge:	Existing models of video captioning use a network and semantics are mixed into one feature.
Approach:	They propose an Adaptive Semantic Guidance Network which instantiates whole video semantics to different POS-aware semantics with supervision of part of speech (POS) tag.
Outcome:	Extensive experiments show that the proposed model is more efficient than state-of-the-art models.

Copied to clipboard

Jiacheng Ye, Ruijian Cai, Tao Gui, Qi Zhang

Learning a Simple and Effective Model for Multi-turn Response Generation with Auxiliary Tasks (2020.emnlp-main)

Challenge:	Existing approaches for keyphrase generation generate uncontrollable and inaccurate absent keyphrases.
Approach:	They propose a graph-based method that captures explicit knowledge from related references.
Outcome:	The proposed model improves on baseline keyphrase generation models on multiple benchmarks.

Copied to clipboard

Yufan Zhao, Can Xu, Wei Wu

Turning Trash into Treasure: Accelerating Inference of Large Language Models with Token Recycling (2025.acl-long)

Challenge:	Existing approaches to multi-turn response generation for open-domain dialogues have a complexity problem . auxiliary tasks that relate to context understanding can guide the learning of the generation model .
Approach:	They propose a multi-turn response generation model that has a simple structure yet can effectively leverage conversation contexts for response generation.
Outcome:	The proposed model outperforms state-of-the-art models in response quality and human judgment . it also enjoys a faster decoding process .

Copied to clipboard

Xianzhen Luo, Yixuan Wang, Qingfu Zhu, Zhiming Zhang, Xuanyu Zhang, Qing Yang, Dongliang Xu

ReCoSa: Detecting the Relevant Contexts with Self-Attention for Multi-turn Dialogue Generation (P19-1)

Challenge:	Large Language Models (LLMs) generate only one token at each decoding step, leading to high latency.
Approach:	They propose a speculative decoding paradigm that stores tokens in an adjacency matrix and employs a breadth-first-search algorithm to construct a draft tree.
Outcome:	The proposed method outperforms existing train-free methods by 30% and even a training method by 25%.

Copied to clipboard

Hainan Zhang, Yanyan Lan, Liang Pang, Jiafeng Guo, Xueqi Cheng

Dialogue Systems & Conversational Agents

Challenge:	Existing hierarchical recurrent encoder-decoder models treat all contexts indiscriminately, which may hurt the following response generation process.
Approach:	They propose a hierarchical recurrent encoder-decoder model that treats all contexts indiscriminately and uses a word level LSTM encoder to obtain the initial representation of each context.
Outcome:	The proposed model outperforms baseline models on Chinese customer services and English Ubuntu dialogue datasets in terms of both metric-based and human evaluations.

Fast and Robust Early-Exiting Framework for Autoregressive Language Models with Synchronized Parallel Decoding (2023.emnlp-main)

Copied to clipboard

Sangmin Bae, Jongwoo Ko, Hwanjun Song, Se-Young Yun

Robustness in NLP

Challenge:	Existing approaches to speed up inference latency have shown performance degradation caused by a state copying mechanism or numerous exit paths.
Approach:	They propose a framework that allocates adaptive computation paths for each token based on the complexity of generating the subsequent token.
Outcome:	The proposed framework outperforms existing frameworks on extensive generation tasks.

Decoding at the Speed of Thought: Harnessing Parallel Decoding of Lexical Units for LLMs (2024.lrec-main)

Copied to clipboard

Chenxi Sun, Hongzhi Zhang, Zijia Lin, Jingyuan Zhang, Fuzheng Zhang, Zhongyuan Wang, Bin Chen, Chengru Song, Di Zhang, Kun Gai, Deyi Xiong

An Effective and Efficient Entity Alignment Decoding Algorithm via Third-Order Tensor Isomorphism (2022.acl-long)

Challenge:	Large language models have demonstrated exceptional capability in natural language understanding and generation, but their generation speed is limited by the inherently sequential nature of their decoding process.
Approach:	They propose a method that accelerates decoding process without sacrificing quality . they propose lexical unit decoding, which can be integrated with other methods .
Outcome:	The proposed method significantly reduces decoding time while maintaining quality while maintaining output quality.

Copied to clipboard

Xin Mao, Meirong Ma, Hao Yuan, Jianchao Zhu, ZongYu Wang, Rui Xie, Wei Wu, Man Lan

Structured Data in NLP

Challenge:	Existing methods focus on graph representation learning, but decoding is a key part of the process.
Approach:	They propose an EA Decoding Algorithm via Third-order Tensor Isomorphism (DATTI) they combine two sets of isomorphic equations to enhance the decoding process .
Outcome:	The proposed algorithm can deliver significant performance improvements even on the most advanced methods while the extra required time is less than 3 seconds.

Your Language Model Can Secretly Write Like Humans: Contrastive Paraphrase Attacks on LLM-Generated Text Detectors (2025.emnlp-main)

Copied to clipboard

Hao Fang, Jiawei Kong, Tianqu Zhuang, Yixiang Qiu, Kuofeng Gao, Bin Chen, Shu-Tao Xia, Yaowei Wang, Min Zhang

Robustness in NLP

Challenge:	Existing methods to detect large language models (LLMs) generated for plagiarism use paraphrases to rewrite them to evade detection.
Approach:	They propose a training-free method that effectively fools text detectors using off-the-shelf LLMs by rewriting them to evade detection.
Outcome:	The proposed method deceives text detectors using off-the-shelf LLMs by rewriting them to produce human-like sentences that are less discernible by detectors.

Answer-driven Deep Question Generation based on Reinforcement Learning (2020.coling-main)

Copied to clipboard

Liuyin Wang, Zihan Xu, Zibo Lin, Haitao Zheng, Ying Shen

Diverse Keyphrase Generation with Neural Unlikelihood Training (2020.coling-main)

Challenge:	Existing methods for deep question generation focus on enhancing document representations, but little attention is paid to the answer information.
Approach:	They propose a deep question generation model that makes better use of the target answer as a guidance to facilitate question generation.
Outcome:	The proposed model outperforms state-of-the-art models in automatic and human evaluations on the hotpotQA dataset.

Copied to clipboard

Hareesh Bahuleyan, Layla El Asri

WatME: Towards Lossless Watermarking Through Lexical Redundancy (2024.acl-long)

Challenge:	Recent advances in neural natural language generation have made possible remarkable progress on the task of keyphrase generation, however, the importance of diversity in keyphrases has been largely ignored.
Approach:	They propose to train a sequence-to-sequence keyphrase generation model from the perspective of diversity.
Outcome:	The proposed model achieves large diversity gains while maintaining competitive output quality.

Copied to clipboard

Liang Chen, Yatao Bian, Yang Deng, Deng Cai, Shuaiyi Li, Peilin Zhao, Kam-Fai Wong

Challenge:	Existing methods for text watermarking rely on arbitrary vocabulary partitioning during decoding, which compromises the availability of suitable tokens and significantly degrades the quality of responses.
Approach:	They propose a method that leverages linguistic prior knowledge of lexical redundancies in LLM vocabularies to seamlessly integrate watermarks.
Outcome:	The proposed approach preserves the expressive power of large language models while preserving watermark detectability.

Long Text Generation by Modeling Sentence-Level and Discourse-Level Coherence (2021.acl-long)

Copied to clipboard

Jian Guan, Xiaoxi Mao, Changjie Fan, Zitao Liu, Wenbiao Ding, Minlie Huang

PostMark: A Robust Blackbox Watermark for Large Language Models (2024.emnlp-main)

Challenge:	Existing generation models struggle to maintain a coherent event sequence throughout the generated text.
Approach:	They propose a long text generation model which can represent prefix sentences at sentence level and discourse level in the decoding process.
Outcome:	The proposed model can generate more coherent texts than state-of-the-art models.

Copied to clipboard

Yapei Chang, Kalpesh Krishna, Amir Houmansadr, John Wieting, Mohit Iyyer

Robustness in NLP

Challenge:	Existing methods to detect LLM-generated text require access to the underlying LLM’s logits, which LLM providers are loath to share due to fears of model distillation.
Approach:	They develop a post-hoc watermarking procedure that inserts an input-dependent set of words into the text after the decoding process has completed.
Outcome:	The proposed method is more robust to paraphrasing attacks than existing methods.

Evolving Sparsity: Leveraging Token Importance Dynamics for Efficient LLM Decoding with Sparse Attention (2026.acl-long)

Copied to clipboard

Ruizi Han, Miao Zhang, Ziyue Qiao, Liqiang Nie

Green & Sustainable NLP

Challenge:	Efficient long-context inference remains a major challenge for large language models (LLMs), as the cost of attention computation during auto-regressive decoding grows linearly with the context length.
Approach:	They propose to model token importance as a dynamic process that evolves over decoding steps and propagates through model layers.
Outcome:	The proposed method outperforms baseline sparse attention methods and achieves speedups of up to 5.36 for attention latency and 2.33 for end-to-end decoding.

Graph-to-Text Generation with Dynamic Structure Pruning (2022.coling-1)

Copied to clipboard

Liang Li, Ruiying Geng, Bowen Li, Can Ma, Yinliang Yue, Binhua Li, Yongbin Li

Structured Data in NLP

Challenge:	Recent studies show that explicitly modeling the input graph structure can significantly improve the performance.
Approach:	They propose a structure-aware cross-attention mechanism to re-encode the graph representation conditioning on the newly generated context at each decoding step.
Outcome:	The proposed model improves performance on two graph-to-text datasets with only minor increase on computational cost.

Multi-Document Scientific Summarization from a Knowledge Graph-Centric View (2022.coling-1)

Copied to clipboard

Pancheng Wang, Shasha Li, Kunyuan Pang, Liangliang He, Dong Li, Jintao Tang, Ting Wang

Information Extraction & Text Mining

Challenge:	Multi-Document Scientific Summarization (MDSS) aims to produce concise and concise summaries for clusters of topic-relevant scientific papers.
Approach:	They propose a model that incorporates knowledge graphs into paper encoding and decoding processes and propose 'decoder' for generating knowledge graph information of summary in the form of descriptive sentences.
Outcome:	The proposed architecture improves on baselines on the Multi-Xscience dataset.

Decoding Matters: Addressing Amplification Bias and Homogeneity Issue in Recommendations for Large Language Models (2024.emnlp-main)

Copied to clipboard

Keqin Bao, Jizhi Zhang, Yang Zhang, Xinyue Huo, Chong Chen, Fuli Feng

Accurate KV Cache Quantization with Outlier Tokens Tracing (2025.acl-long)

Challenge:	Existing approaches to adapt Large Language Models (LLMs) for recommendation encounter significant challenges such as amplification bias and homogeneity.
Approach:	They propose a new decoding approach called Debiasing-Diversifying Decoding (D3) that disables length normalization for ghost tokens to alleviate amplification bias and incorporates a text-free assistant model to encourage tokens less frequently generated by LLMs for counteracting recommendation homogeneity.
Outcome:	Extensive experiments on real-world datasets demonstrate the proposed approach’s effectiveness in enhancing accuracy and diversity.

Copied to clipboard

Yi Su, Yuechi Zhou, Quantong Qiu, Juntao Li, Qingrong Xia, Ping Li, Xinyu Duan, Zhefeng Wang, Min Zhang

Bridging by Word: Image Grounded Vocabulary Construction for Visual Captioning (P19-1)

Challenge:	Large Language Models (LLMs) require substantial computational resources during deployment.
Approach:	They propose a method to identify outlier tokens and exclude them from quantization . they find that the method can deliver a 6.4 times reduction in memory usage and a 2.5 times increase in throughput .
Outcome:	The proposed method delivers a 6.4 times reduction in memory usage and a 2.5 times increase in throughput under 2-bit quantization.

Copied to clipboard

Zhihao Fan, Zhongyu Wei, Siyuan Wang, Xuanjing Huang

Parallel Refinements for Lexically Constrained Text Generation with BART (2021.emnlp-main)

Challenge:	Existing research on image captioning generates frequent n-grams with irrelevant words.
Approach:	They propose to construct an image-grounded vocabulary incorporating visual information and relations among words into the decoding process directly.
Outcome:	The proposed framework is compared with state-of-the-art models on MS COCO and Flickr30k and shows that it is more efficient than existing models.

Copied to clipboard

Xingwei He

Dynamic Stochastic Decoding Strategy for Open-Domain Dialogue Generation (2024.findings-acl)

Challenge:	Existing work injects lexical constraints into the output, which generates generic or ungrammatical sentences and has high computational complexity.
Approach:	They propose a model that incorporates pre-specified keywords into the output to control the generated text.
Outcome:	The proposed model decomposes the generated text into two sub-tasks and improves the sentence quality.

Copied to clipboard

Yiwei Li, Fei Mi, Yitong Li, Yasheng Wang, Bin Sun, Shaoxiong Feng, Kan Li

Dialogue Systems & Conversational Agents

Challenge:	Stochastic sampling strategies are not widely used in open-domain dialogue systems.
Approach:	They propose a dynamic decoding strategy which can adjust the decoding space w.r.t. different contexts.
Outcome:	The proposed decoding strategy can improve the performance of pre-trained models when coupled with four well-used stochastic decoding algorithms.

Prefix Text as a Yarn: Eliciting Non-English Alignment in Foundation Language Model (2024.findings-acl)

Copied to clipboard

Runzhe Zhan, Xinyi Yang, Derek Wong, Lidia Chao, Yue Zhang

Chunk, Align, Select: A Simple Long-sequence Processing Method for Transformers (2024.acl-long)

Challenge:	supervised fine-tuning (SFT) has been a straightforward approach for tailoring the output of foundation large language models (LLMs) to specific preferences.
Approach:	They propose a training-free alignment method that uses minimal prior tokens to bridge the foundation LLM and the SFT LLM.
Outcome:	The proposed method achieves comparable performance without training on machine translation and part-of-speech tagging across seven languages.

Copied to clipboard

Jiawen Xie, Pengyu Cheng, Xiao Liang, Yong Dai, Nan Du

Temperature-Centric Investigation of Speculative Decoding with Knowledge Distillation (2024.findings-emnlp)

Challenge:	Existing transformer-based models struggle with long-sequence processing due to computational costs . a framework to enhance long-content processing of transformers is proposed .
Approach:	They propose a framework to enhance long-sequence processing of transformers by three steps . they demonstrate that the framework significantly outperforms prior long-quence processors .
Outcome:	The proposed framework outperforms baseline models on long-sequence summarization and reading comprehension tasks.

Copied to clipboard

Siru Ouyang, Shuohang Wang, Minhao Jiang, Ming Zhong, Donghan Yu, Jiawei Han, Yelong Shen

Explicit Syntactic Guidance for Neural Text Generation (2023.acl-long)

Challenge:	Speculative decoding is a novel method to expedite inference in autoregressive (large) language models.
Approach:	They propose to use a smaller model as a draft model to speculate a block of tokens, which the target model then evaluates for acceptance.
Outcome:	The proposed method can be used to accelerate inference in autoregressive (large) language models by using smaller models as draft models to speculate tokens for multiple inference steps.

Copied to clipboard

Yafu Li, Leyang Cui, Jianhao Yan, Yongjing Yin, Wei Bi, Shuming Shi, Yue Zhang

Syntactic Text Processing

Challenge:	Existing text generation models follow the sequence-to-sequence paradigm . generative grammar suggests humans generate language by learning language grammar .
Approach:	They propose a syntax-guided generation schema that searches the syntax tree in a top-down direction.
Outcome:	The proposed method outperforms autoregressive baselines on paraphrase generation and machine translation.

Towards Unified Spoken Language Understanding Decoding via Label-aware Compact Linguistics Representations (2023.findings-acl)

Copied to clipboard

Zhihong Zhu, Xuxin Cheng, Zhiqi Huang, Dongsheng Chen, Yuexian Zou

Intent-Aware and Hate-Mitigating Counterspeech Generation via Dual-Discriminator Guided LLMs (2024.lrec-main)

Challenge:	Existing methods for intent detection and slot filling decoders could result in misaligned predictions for both tasks.
Approach:	They propose a method that leverages label embeddings to jointly guide the decoding process.
Outcome:	The proposed method outperforms existing methods on two single- and multi-intent SLU benchmarks and can be incorporated into existing models.

Copied to clipboard

Haiyang Wang, Zhiliang Tian, Xin Song, Yue Zhang, Yuchen Pan, Hongkui Tu, Minlie Huang, Bin Zhou

Responsible & Trustworthy NLP

Challenge:	Hate speech is an aggressive expression that incites hatred towards specific groups based on their group identity.
Approach:	They propose an LLMs-based framework for counterspeech generation that uses intent-aware discriminators to decode intents of LLM models.
Outcome:	The proposed framework matches intents with hate mitigation intents and performs well.

ECHA: Jailbreaking LVLMs via the Mismatch between Implicit Semantic Reconstruction and Explicit Safety Alignment (2026.findings-acl)

Copied to clipboard

Chenxing Xu, Junyong Jiang, Zehu Zhang, Lu Dong

SafeSteer: A Decoding-level Defense Mechanism for Multimodal Large Language Models (2026.findings-acl)

Challenge:	Existing safety guardrails fail to intercept latent intent, whereas LVLMs can implicitly synthesize holistic malicious semantics from fragmented visual cues.
Approach:	They propose an Emoji Chain Hinting Attack (ECHA) framework that decouples sensitive concepts into semantically related emoji chains and structural text masks.
Outcome:	The proposed framework outperforms existing baselines and bypasses safety guardrails in over 81% of instances with a single attempt.

Copied to clipboard

Xinyi Zeng, Xue Yang, Jingyuan Zhang, Huanqian Yan, Xiang Chen, Kaiwen Wei, Hankun Kang, Yu Tian

Responsible & Trustworthy NLP

Challenge:	Existing defense methods rely on fine-tuning or inefficient post-hoc interventions, limiting their ability to address novel attacks.
Approach:	They propose a decoding-level defense mechanism that employs a lightweight discriminator to iteratively steer the decoding process toward safety.
Outcome:	The proposed method improves safety performance by up to 33.40% without fine-tuning on multiple MLLMs.

DeCoVec: Building Decoding Space based Task Vector for Large Language Models via In-Context Learning (2026.findings-acl)

Copied to clipboard

Feiyang Li, Yile Wang

1-PAGER: One Pass Answer Generation and Evidence Retrieval (2023.findings-emnlp)

Challenge:	Existing approaches to steering large language models require fine-tuning or manipulation of internal states, limiting their flexibility and scalability.
Approach:	They propose a framework that constructs task vectors directly in the decoding space by leveraging in-context learning.
Outcome:	The proposed framework outperforms standard few-shot baselines on TruthfulQA, Math-500, and AQUA-RAT with gains up to +5.50 accuracy.

Copied to clipboard

Palak Jain, Livio Soares, Tom Kwiatkowski

Information Retrieval

Challenge:	1-Pager is the first system that answers a question and retrieves evidence using a single Transformer-based model and decoding process.
Approach:	They propose a system that partitions the corpus using constrained decoding to select a document and answer string, and a method that uses a single Transformer-based model to generate evidence.
Outcome:	The proposed system outperforms the equivalent ‘closed-book’ question answering model by grounding predictions in evidence corpus.

Concise and Precise Context Compression for Tool-Using Language Models (2024.findings-acl)

Copied to clipboard

Yang Xu, Yunlong Feng, Honglin Mu, Yutai Hou, Yitong Li, Xinghao Wang, Wanjun Zhong, Zhongyang Li, Dandan Tu, Qingfu Zhu, Min Zhang, Wanxiang Che

GRACE: Discriminator-Guided Chain-of-Thought Reasoning (2023.findings-emnlp)

Challenge:	Existing methods suffer from key information loss and difficulty in adjusting the length of compressed sequences based on documentation lengths.
Approach:	They propose two strategies for compressing tool documentation into concise and precise summary sequences for tool-using language models.
Outcome:	The proposed approach achieves comparable performance to the upper-bound baseline under 16x compression ratio.

Copied to clipboard

Muhammad Khalifa, Lajanugen Logeswaran, Moontae Lee, Honglak Lee, Lu Wang

Reasoning

Challenge:	Existing language models (LMs) can assign a high likelihood to incorrect steps . Existing models (LLMs), however, struggle with complex multi-step reasoning.
Approach:	They propose a stepwise decoding approach that steers the decoding process towards producing correct reasoning steps.
Outcome:	The proposed approach outperforms existing methods on math and symbolic reasoning tasks.

SPIDE: Serial and Parallel Intertwined Speculative Decoding (2026.findings-acl)

Copied to clipboard

Wenru Xu, Peixuan Xu, Ziqi Yang, Ming Hu, Zihui Wang, Jianzhong Qi, Rongshan Yu, Xiaoliang Fan, Cheng Wang

Green & Sustainable NLP

Challenge:	Speculative decoding (SD) is a training-free SD framework that orchestrates dynamic alternation combining serial dynamic drafting with parallel draft verification.
Approach:	They propose a serial and parallel intertwined speculative DEcoding framework that orchestrates dynamic alternation combining serial dynamic drafting and parallel draft verification.
Outcome:	The proposed framework accelerates inference while reducing the LLM usage costs.

Decoding on Graphs: Faithful and Sound Reasoning on Knowledge Graphs through Generation of Well-Formed Chains (2025.acl-long)

Copied to clipboard

Kun Li, Tianhua Zhang, Xixin Wu, Hongyin Luo, James R. Glass, Helen M. Meng

Structured Data in NLP

Challenge:	Existing research on the utilization of Knowledge Graphs (KGs) for large language models (LLMs) relies on subgraph retriever or iterative prompting, overlooking the potential synergy of LLMs’ step-wise reasoning capabilities and KGs’ structural nature.
Approach:	They propose a graph-aware constrained decoding framework that facilitates a deep synergy between LLMs and KGs by constraint derived from the topology of the KG.
Outcome:	The proposed framework can provide faithful and sound reasoning for KGQA.

Token-level Inference-Time Alignment for Vision-Language Models (2026.findings-acl)

Copied to clipboard

Kejia Chen, Junjun Zheng, Jiawen Zhang, Manxi Lin, Xiao Pan, Jiacong Hu, Jian Lou, Zunlei Feng, Mingli Song

Let’s Fuse Step by Step: A Generative Fusion Decoding Algorithm with LLMs for Robust and Instruction-Aware ASR and OCR (2025.findings-acl)

Challenge:	Vision-Language Models (VLMs) often prioritize linguistic fluency over visual fidelity . despite widespread adoption, VLMs often exhibit a critical failure mode: hallucination .
Approach:	They propose a framework for Token-level Inference-Time Alignment that steers the decoding process without updating the base model parameters.
Outcome:	The proposed framework improves performance on 13 benchmarks across architectures . it boosts LLaVA-1.5-7B by 8.6% on MMVet and achieves a 74.0 MMStar score .

Copied to clipboard

Chan-Jan Hsu, Yi-Chang Chen, Feng-Ting Liao, Pei-Chen Ho, Yu-Hsiang Wang, Po-Chun Hsu, Da-shan Shiu

Cautious Next Token Prediction (2025.findings-acl)

Challenge:	Various fusion strategies have been explored for integration of large language models into multi-modal systems.
Approach:	They propose a framework for deep fusion decoding that integrates large language models into cross-modal text recognition systems.
Outcome:	The proposed framework surpasses cascaded methods in English and Mandarin, and significantly reduces WERs by 17.7%.

Copied to clipboard

Yizhou Wang, Lingzhi Zhang, Yue Bai, Mang Tik Chiu, Zhengmian Hu, Mingyuan Zhang, Qihua Dong, Yu Yin, Sohrab Amirghodsi, Yun Fu

Challenge:	Existing methods for decoding autoregressive models are temperature scaling and nucleus sampling to balance diversity and coherence.
Approach:	They propose a training-free decoding strategy that uses a model with a low perplexity score to select the trial with the lowest perplexities as the most probable and reliable path.
Outcome:	The proposed approach outperforms existing standard decoding strategies consistently by a clear margin.

IntentCoding: Amplifying User Intent in Code Generation (2026.findings-acl)

Copied to clipboard

Zheng Fang, Yihong Dong, Lili Mou, Dongming Jin, Zhi Jin, Ge Li