Papers with plug-and-play method
Extending LLM Context Window with Adaptive Grouped Positional Encoding: A Training-Free Method (2025.acl-long)
Copied to clipboard
| Challenge: | Existing long-context training data is scarce and requires substantial GPU resources for training. |
| Approach: | They propose a training-free plug-and-play method to enhance long-context understanding in existing large language models. |
| Outcome: | The proposed method outperforms existing LLMs on various tasks and surpasses baseline methods. |
Zero-Shot Text Classification with Self-Training (2022.emnlp-main)
Copied to clipboard
| Challenge: | Recent advances in large pretrained language models have increased attention to zero-shot text classification. |
| Approach: | They propose a plug-and-play method to bridge this gap by requiring only class names along with an unlabeled dataset. |
| Outcome: | The proposed model can be trained on a natural language inference dataset and performs on dozens of unseen tasks without the need for domain expertise or trial and error. |
Mitigating Hallucinations in Multi-modal Large Language Models via Image Token Attention-Guided Decoding (2025.naacl-long)
Copied to clipboard
| Challenge: | Multi-modal large language models (MLLMs) generate plausible but incorrect content, resulting in hallucinations . recent advances in MLLM technology have demonstrated their outstanding performance in a variety of visual tasks, such as object detection. |
| Approach: | They propose a plug-and-play method which leverages MLLMs’ internal representations to mitigate hallucinations by analyzing input and output tokens. |
| Outcome: | The proposed method exploits MLLMs’ internal representations to mitigate hallucinations. |
Draft on the Fly: Adaptive Self-Speculative Decoding using Cosine Similarity (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Speculative decoding uses a small draft model to generate a single input token, instead of sequentially generating tokens until completion. |
| Approach: | They propose a method that generates varying draft models adapted to the input context using simple rules. |
| Outcome: | The proposed method is competitive with the current SOTA for self-speculative decoding while being a truly plug-and-play method. |
Calibrating the Confidence of Large Language Models by Eliciting Fidelity (2024.emnlp-main)
Copied to clipboard
| Challenge: | Large language models with RLHF and RLAIF have good alignment but exhibit overconfidence post-alignment. |
| Approach: | They propose a plug-and-play method to estimate the confidence of large language models. |
| Outcome: | The proposed method has shown good calibration performance on 6 RLHF-LMs on four MCQA datasets. |
Improve Safety Training of Large Language Models with Safety-Critical Singular Vectors Localization (2025.acl-long)
Copied to clipboard
| Challenge: | Recent work on safety training with modules such as low-rank adaptation (LoRA) to resist jailbreaks shows promise, but these approaches can inadvertently degrade a model’s general utility. |
| Approach: | They propose a plug-and-play method that locates safety-critical singular vectors within the model's parameter space and a dynamic rank number determination strategy to reduce parameter overhead. |
| Outcome: | The proposed method mitigates the impact of safety training on model utility by explicitly locating and leveraging safety-critical singular vectors within the model’s parameter space. |
Exploiting Intrinsic Multilateral Logical Rules for Weakly Supervised Natural Language Video Localization (2024.acl-long)
Copied to clipboard
| Challenge: | Existing methods for WS-NLVL rarely consider complex temporal relations enclosing the language query, yielding illogical predictions. |
| Approach: | They propose a plug-and-play method to exploit temporal relations and logical rules for WS-NLVL. |
| Outcome: | The proposed method is able to retrieve the moment corresponding to a language query in a video with only video-language pairs utilized during training. |
Robust Preference Optimization via Dynamic Target Margins (2025.findings-acl)
Copied to clipboard
| Challenge: | Direct Preference Optimization (DPO) is an efficient method for ensuring safety and reliability in practical applications. |
| Approach: | They propose a dynamic target margin preference optimization algorithm that adjusts reward margins at the pairwise level. |
| Outcome: | The proposed method achieves an average 4.4% improvement over baselines, setting new benchmarks for state-of-the-art performance. |
MixKVQ: Query-Aware Mixed-Precision KV Cache Quantization for Long-Context Reasoning (2026.acl-long)
Copied to clipboard
| Challenge: | Existing low-bit quantization methods often exhibit severe performance degradation on complex reasoning tasks. |
| Approach: | They propose a plug-and-play method that uses a key channel's intrinsic quantization difficulty and relevance to the query to identify and preserve critical key channels that need higher precision. |
| Outcome: | Experiments on complex reasoning datasets show that the proposed method outperforms low-bit methods at a substantially reduced memory footprint. |
ComCLIP: Training-Free Compositional Image and Text Matching (2024.naacl-long)
Copied to clipboard
| Challenge: | erroneous semantics of individual entities are essentially confounders that cause the matching failure. |
| Approach: | They propose a training-free compositional CLIP model which disentangles input images into subjects, objects, and action subimages and composes CLIP’s vision encoder and text encoder to perform evolving matching over compositional text embedding and subimage embeddments. |
| Outcome: | The proposed model mitigates spurious correlations introduced by the pretrained CLIP models and dynamically evaluates the importance of each component. |
Logical Closed Loop: Uncovering Object Hallucinations in Large Vision-Language Models (2024.findings-acl)
Copied to clipboard
| Challenge: | Object hallucination has been an Achilles’ heel which hinders the broader applications of large vision-language models (LVLMs). |
| Approach: | They propose a logical closed loop-based framework for Object Hallucination Detection and Mitigation that uses logical consistency probing to raise questions with logical correlations to determine hallucinations. |
| Outcome: | The proposed method can be applied to all existing LVLMs and is effective and general. |
CGBridge: Bridging Code Graphs and Large Language Models for Better Structure-Aware Code Understanding (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing structure-aware approaches treat structure as serialized text prompts or auxiliary training objectives, failing to provide explicit guidance during inference. |
| Approach: | They propose a plug-and-play method that enhances Large Language Models with Code Graph information through an external, trainable Bridge module. |
| Outcome: | The proposed method decouples structural reasoning from textual generation without updating the backbone. |
Self-Reflective Generation at Test Time (2026.acl-long)
Copied to clipboard
| Challenge: | Existing self-reflection mechanisms are reactive and inefficient for large language models . a fundamental tension persists between the ability to execute complex multi-step reasoning and the ability of the model to generate coherent traces. |
| Approach: | They propose a test-time framework that reflects before generating at uncertain points . SRGen utilizes dynamic entropy thresholding to identify high-uncertainty tokens . |
| Outcome: | The proposed framework can significantly strengthen large language models' reasoning process. |
PrivacyRestore: Privacy-Preserving Inference in Large Language Models via Privacy Removal and Restoration (2025.acl-long)
Copied to clipboard
| Challenge: | Existing privacy protection methods for large language models suffer from performance degradation or large inference time overhead. |
| Approach: | They propose a plug-and-play method to protect the privacy of user inputs during LLM inference . they use offline restoration vectors to train restoration vector for each privacy span type . |
| Outcome: | The proposed method can prevent the linear growth of the privacy budget. |
Steering LVLMs via Sparse Autoencoder for Hallucination Mitigation (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Existing approaches to address hallucinations in large vision-language models require substantial computational cost and time. |
| Approach: | They propose to leverage sparse autoencoders to identify semantic directions closely associated with faithfulness or hallucination, extracting more precise and disentangled hallucinian-related representations. |
| Outcome: | The proposed method outperforms existing decoding approaches while maintaining transferability across different model architectures with negligible additional time overhead. |
Think and Recall: Layer-Level Prompting for Lifelong Model Editing (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods for lifelong model editing suffer from limitations in usability, such as requiring additional training corpora or lacking support for reversible and detachable edits. |
| Approach: | They propose a plug-and-play method for knowledge retrieval and storage, i.e., Layer-Level Prompting, which enables seamless and efficient lifelong model editing. |
| Outcome: | The proposed method outperforms existing methods on question answering and hallucination benchmarks across different LLMs. |
CED: Comparing Embedding Differences for Detecting Out-of-Distribution and Hallucinated Text (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods for detecting out-of-distribution (OOD) samples are limited due to their domain shift and computational limitations. |
| Approach: | They propose a training-free method to detect out-of-distribution (OOD) samples . they theoretically validate that specific auxiliary and oracle samples improve this distinction . |
| Outcome: | The proposed method improves the ability of pre-trained models to distinguish between ID and OOD samples in text classification and hallucination detection tasks. |
Speculative Streaming: Efficient and Scalable Speculative Decoding with Multi-Stream Attention (2025.emnlp-main)
Copied to clipboard
Nikhil Bhendawade, Irina Belousova, Qichen Fu, Henry Mason, Antonie Lin, Mohammad Rastegari, Mahyar Najibi
| Challenge: | Speculative decoding is a prominent technique for accelerating LLM inference by leveraging an auxiliary draft model, but its effectiveness is limited by the autoregressive nature of draft generation. |
| Approach: | They propose a method that integrates speculative draft generation directly within the target model using multi-stream attention. |
| Outcome: | The proposed method improves acceptance but also latency and speculation latency, limiting overall speedup. |
Attention Basin: Why Contextual Position Matters in Large Language Models (2026.acl-long)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) are sensitive to the contextual position of information in input. |
| Approach: | They introduce Attention-Driven Reranking (AttnRank) which estimates a model’s intrinsic positional attention preferences using a small calibration set and reorders retrieved documents or few-shot examples to align the most salient content with these high-attention positions. |
| Outcome: | Experiments on multi-hop QA and few-shot in-context learning tasks show that AttnRank achieves substantial improvements across 10 large language models of varying architectures and scales, without modifying model parameters or training procedures. |