Papers with inference phase
Extract-Select: A Span Selection Framework for Nested Named Entity Recognition with Generative Adversarial Training (2022.findings-acl)
Copied to clipboard
| Challenge: | Existing studies treat named entity recognition as a sequential labeling problem. |
| Approach: | They propose a span selection framework for nested named entity recognition . they propose nesting entities with different input categories would be separately extracted . |
| Outcome: | The proposed framework outperforms competing models on four benchmark datasets. |
Hashing based Efficient Inference for Image-Text Matching (2021.findings-acl)
Copied to clipboard
| Challenge: | Recent work on image-text matching has focused on exploring interactions between images and sentences to improve performance without considering inference efficiency. |
| Approach: | They propose a hashing-based efficient inference module which can be plugged into existing frameworks to speed up inference step without reducing retrieval performance. |
| Outcome: | The proposed module can be plugged into existing framework to speed up inference step without reducing retrieval performance. |
ProphetChat: Enhancing Dialogue Generation with Simulation of Future Conversation (2022.acl-long)
Copied to clipboard
| Challenge: | generative dialogue models use dialogue histories to generate the response . however, generating a response based on the historical information is not easy . |
| Approach: | They propose a framework that utilizes simulated dialogue futures to enhance response generation. |
| Outcome: | The proposed framework can generate better responses over strong baselines on two open-domain dialogue datasets. |
A Multi-task Learning Framework for Opinion Triplet Extraction (2020.findings-emnlp)
Copied to clipboard
| Challenge: | Existing approaches to Aspect-based sentiment analysis (ABSA) use aspect terms and their corresponding sentiment polarities as a reference, but they lack opinion terms as . |
| Approach: | They propose a multi-task learning framework to extract aspect terms and opinion terms and parse their sentiment dependencies with a biaffine scorer. |
| Outcome: | The proposed framework outperforms baseline and state-of-the-art approaches on four SemEval benchmarks. |
A Query-Parallel Machine Reading Comprehension Framework for Low-resource NER (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Named entity recognition (NER) is a fundamental task in natural language processing. |
| Approach: | They propose a query-parallel MRC-based approach to named entity recognition . the model is trained with parameter-efficient tuning technique, making it more data-efficient . |
| Outcome: | The proposed model performs competitively against strong baseline methods in resource-rich settings and achieves state-of-the-art results in low-resource settings. |
Plug-in Language Model: Controlling Text Generation with a Simple Regression Model (2024.findings-naacl)
Copied to clipboard
| Challenge: | Large-scale pre-trained language models have demonstrated unrivaled capacity in generating text that closely resembles human-written content. |
| Approach: | They propose a plug-in language model that leverages reinforcement learning to adjust latent states to control text generation. |
| Outcome: | The proposed model outperforms existing methods that rely on gradient-based, weighted decoding, or prompt-based methods. |
Distill The Image to Nowhere: Inversion Knowledge Distillation for Multimodal Machine Translation (2022.emnlp-main)
Copied to clipboard
| Challenge: | Existing studies on multimodal machine translation (MMT) have focused on the fusion and alignment of images and texts to improve MMT. |
| Approach: | They propose an image-free inference framework that supports image-based inference via an inversion knowledge distillation scheme. |
| Outcome: | The proposed framework is the first to rival or surpass image-must frameworks on the multimodal translation benchmark. |
TextMixer: Mixing Multiple Inputs for Privacy-Preserving Inference (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Pre-trained language models (PLMs) are often deployed as cloud services, enabling users to upload textual data and perform inference remotely. |
| Approach: | They propose a privacy-preserving inference framework called MixPi which aims to obfuscate a user's private input by mixing it with multiple other inputs. |
| Outcome: | The proposed framework surpasses existing privacy-preserving methods on token and sentence classification tasks. |
Re-Invoke: Tool Invocation Rewriting for Zero-Shot Tool Retrieval (2024.findings-emnlp)
Copied to clipboard
Yanfei Chen, Jinsung Yoon, Devendra Sachan, Qingze Wang, Vincent Cohen-Addad, Mohammadhossein Bateni, Chen-Yu Lee, Tomas Pfister
| Challenge: | Recent advances in large language models have enabled autonomous agents with complex reasoning and task-fulfillment capabilities using a wide range of tools. |
| Approach: | They propose an unsupervised tool retrieval method that leverages LLM’s query understanding capabilities to extract key tool-related context and underlying intents from user queries. |
| Outcome: | The proposed method significantly outperforms state-of-the-art tools in single-tool and multi-tool scenarios, all within a fully unsupervised setting. |
MuMath-Code: Combining Tool-Use Large Language Models with Multi-perspective Data Augmentation for Mathematical Reasoning (2024.emnlp-main)
Copied to clipboard
| Challenge: | a method to combine the advantages of open-source and tool-free LLMs remains to be explored. |
| Approach: | They propose a method to integrate open-source LLMs with external Python interpreters and augment math reasoning data. |
| Outcome: | The proposed method improves on GSM8K and MATH with the use of external tools. |
IM-TQA: A Chinese Table Question Answering Dataset with Implicit and Multi-type Table Structures (2023.acl-long)
Copied to clipboard
| Challenge: | Existing benchmarks only evaluate model performance on tables with explicit table structures, which means headers are explicitly annotated and treated as model input during inference. |
| Approach: | They propose a new Table Question Answering (TQA) dataset with implicit and multi-type table structures that requires the model to understand tables without directly available header annotations. |
| Outcome: | The proposed framework outperforms baselines on a dataset with implicit and multi-type table structures and can handle multi-table tables including previously neglected complex tables. |
Open World Classification with Adaptive Negative Samples (2022.emnlp-main)
Copied to clipboard
| Challenge: | Existing models with no effective open category data during training are limited by the lack of effective open categories data during the training stage. |
| Approach: | They propose an approach to generate effective open category samples in the training stage and without requiring prior knowledge or external datasets. |
| Outcome: | The proposed approach generates effective synthetic open category samples in the training stage and without requiring any prior knowledge or external datasets. |
Zipage: Maintain High Request Concurrency for LLM Reasoning through Compressed PagedAttention (2026.findings-acl)
Copied to clipboard
Mengqi Liao, Lu Wang, Chaoyun Zhang, Bo Qiao, Si Qin, Qingwei Lin, Saravan Rajmohan, Dongmei Zhang, Huaiyu Wan
| Challenge: | Existing methods to evict KV cache during inference phase are impractical for industrial-grade applications. |
| Approach: | They propose a method that combines token-wise KV cache eviction with PagedAttention and propose 'zipage' it achieves 95% of the performance of Full KV inference engines while delivering over 2.1 speedup . |
| Outcome: | The proposed method achieves 95% of the performance of Full KV inference engines while delivering over 2.1 speedup on large-scale mathematical reasoning tasks. |
Boosting Policy and Process Reward Models with Monte Carlo Tree Search in Open-Domain QA (2025.findings-acl)
Copied to clipboard
Chi-Min Chan, Chunpu Xu, Junqi Zhu, Jiaming Ji, Donghai Hong, Pengcheng Wen, Chunyang Jiang, Zhen Ye, Yaodong Yang, Wei Xue, Sirui Han, Yike Guo
| Challenge: | Experimental results show that our approach can effectively improve the performance of both the policy model and the reward model. |
| Approach: | They propose to use Monte Carlo Tree Search for both policy model improvement and reward model improvement to bridge it to more subtle open-domain question answering. |
| Outcome: | The proposed approach surpasses existing methods for annotation and training data with fewer data points and achieves better performance in test-time scaling strategies. |
Effects of sub-word segmentation on performance of transformer language models (2023.emnlp-main)
Copied to clipboard
| Challenge: | Language models are a fundamental task in natural language processing, but few studies focus on the effect of sub-word segmentation on the performance of models. |
| Approach: | They compare GPT and BERT models trained with statistical segmentation algorithm BPE to unsupervised morphological segmentation algorithms Morfessor and StateMorph. |
| Outcome: | The proposed model trains for several languages and compares them with two unsupervised morphological segmentation algorithms. |
LLM-guided Plan and Retrieval: A Strategic Alignment for Interpretable User Satisfaction Estimation in Dialogue (2025.naacl-long)
Copied to clipboard
| Challenge: | Existing methods for estimating user satisfaction with dialogue systems face challenges due to limited understanding of underlying reasons for user dissatisfaction and high costs of annotating user intentions. |
| Approach: | They propose an interpretable framework for effective user satisfaction prediction . they propose to align utterances with strategies and large language models to retrieve relevant features from utterations. |
| Outcome: | The proposed framework achieves state-of-the-art performance on three benchmarks for the USE task. |
Dialogizer: Context-aware Conversational-QA Dataset Generation from Textual Sources (2023.emnlp-main)
Copied to clipboard
| Challenge: | Existing dialog inpainting methods generate ConvQA datasets with low contextual relevance due to insufficient learning of question-answer alignment. |
| Approach: | They propose a dialog inpainting method that generates ConvQA datasets from documents . they propose re-ranking tasks and a framework that generate contextually relevant questions . |
| Outcome: | The proposed framework generates ConvQA datasets with high contextual relevance from textual sources. |
InferAligner: Inference-Time Alignment for Harmlessness through Cross-Model Guidance (2024.emnlp-main)
Copied to clipboard
Pengyu Wang, Dong Zhang, Linyang Li, Chenkun Tan, Xinghao Wang, Mozhi Zhang, Ke Ren, Botian Jiang, Xipeng Qiu
| Challenge: | Existing methods for enhancing harmlessness and helpfulness of large language models (LLMs) involve complex and resource-intensive training processes. |
| Approach: | They propose a method that decouples harmlessness from helpfulness during inference phase. |
| Outcome: | The proposed method significantly reduces the attack success rate (ASR) of harmful instructions and jailbreak instructions while maintaining almost unchanged performance in downstream tasks. |
High-order Joint Constituency and Dependency Parsing (2024.lrec-main)
Copied to clipboard
| Challenge: | Syntactic parsing aims to reveal how sentences are syntactically structured. |
| Approach: | They propose to produce compatible constituency and dependency trees simultaneously for input sentences . they adopt a much more efficient decoding algorithm and explore joint modeling at training phase . |
| Outcome: | The proposed model significantly improves matching ratio of whole trees compared to separate models . the proposed model adopts a much more efficient decoding algorithm . |
MoSE: Modality Split and Ensemble for Multimodal Knowledge Graph Completion (2022.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods to predict missing entities share relation representation across modalities, which results in mutual interference between modality. |
| Approach: | They propose a framework for multimodal knowledge graph completion that learns modality-split relation embeddings for each modality instead of a single modality shared one. |
| Outcome: | The proposed framework outperforms state-of-the-art methods on three KG datasets. |
Cross-modality Information Check for Detecting Jailbreaking in Multimodal Large Language Models (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Multimodal Large Language Models (MLLMs) are susceptible to jailbreak attacks, authors say . multimodal information increases the risk of attacks, but also provides additional data . |
| Approach: | They propose a jailbreaking detector that detects maliciously perturbed image inputs . cross-modality information detector is designed to detect cross-modal similarity between harmful queries and adversarial images. |
| Outcome: | a new tool can detect maliciously perturbed image inputs without modification or computation cost. |
DiffPO: Diffusion-styled Preference Optimization for Inference Time Alignment of Large Language Models (2025.acl-long)
Copied to clipboard
Ruizhe Chen, Wenhao Chai, Zhifei Yang, Xiaotian Zhang, Ziyang Wang, Tony Quek, Joey Tianyi Zhou, Soujanya Poria, Zuozhu Liu
| Challenge: | Inference-time alignment approaches still face limitations due to policy-specific value functions and latency during the inference phase. |
| Approach: | They propose an efficient and policy-agnostic preference optimization method that avoids time latency associated with token generation. |
| Outcome: | The proposed method achieves a favorable trade-off between alignment quality and inference-time latency. |
FAQ: Mitigating Quantization Error via Regenerating Calibration Data with Family-Aware Quantization (2026.findings-acl)
Copied to clipboard
| Challenge: | representativeness and universality of calibration data remain a bottleneck in quantization accuracy. |
| Approach: | They propose a framework that leverages prior knowledge from LLMs to generate calibration samples . their framework reduces accuracy loss by up to 28.5% compared to baseline . |
| Outcome: | Experiments show that family-aware quantization reduces accuracy loss by up to 28.5% compared to baseline data. |
DISC: Plug-and-Play Decoding Intervention with Similarity of Characters for Chinese Spelling Check (2025.acl-long)
Copied to clipboard
Ziheng Qiao, Houquan Zhou, Yumeng Liu, Zhenghua Li, Min Zhang, Bo Zhang, Chen Li, Ji Zhang, Fei Huang
| Challenge: | Chinese spelling check (CSC) tasks require that incorrect characters are usually similar to the correct ones in either phonetics or glyph. |
| Approach: | They propose a plug-and-play decoding intervention with similarity of characters module for Chinese spelling check (CSC) they propose to incorporate phonetic and glyph similarities only during the inference phase. |
| Outcome: | The proposed method significantly improves Chinese spelling check models on benchmarks and on benchmark datasets. |