Papers with long-context scenarios
RoBSA: RoPE-based Blockwise Sparse Multi-head Latent Attention (2026.acl-long)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) have advanced in recent years, scaling up in both parameter count and context length. |
| Approach: | They propose a method to compute attention over a subset of context tokens and to implement token selection in a blockwise manner. |
| Outcome: | The proposed method reduces end-to-end inference latency by up to 2.55x with minimal accuracy loss compared to full attention in long-context scenarios for very large models. |
LongSpec: Long-Context Lossless Speculative Decoding with Efficient Drafting and Verification (2026.acl-long)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) can process extremely long contexts, requiring efficient inference over extended inputs. |
| Approach: | They propose a model that uses a constant-sized key-value cache to train long-context models. |
| Outcome: | Experimental results show that LongSpec achieves 3.26x speedup over strong Flash Attention baselines and 2.34x wall clock time on four math reasoning tasks. |
Tagging-Augmented Generation: Assisting Language Models in Finding Intricate Knowledge In Long Contexts (2025.emnlp-industry)
Copied to clipboard
Anwesan Pal, Karen Hovsepian, Tinghao Guo, Mengnan Zhao, Somendra Tripathi, Nikos Kanakaris, George Mihaila, Sumit Nigam
| Challenge: | Recent studies into effective context lengths of flagship large language models (LLMs) have revealed major limitations in effective question answering (QA) and reasoning over long and complex contexts for even the largest and most impressive cadre of models. |
| Approach: | They propose a lightweight data augmentation strategy that boosts LLM performance in long-context scenarios without degrading and altering the integrity and composition of retrieved documents. |
| Outcome: | The proposed strategy boosts performance in long-context scenarios without degrading and altering the integrity and composition of retrieved documents. |
Multimodal Needle in a Haystack: Benchmarking Long-Context Capability of Multimodal Large Language Models (2025.naacl-long)
Copied to clipboard
Hengyi Wang, Haizhou Shi, Shiwei Tan, Weiyi Qin, Wenyuan Wang, Tunyu Zhang, Akshay Nambi, Tanuja Ganu, Hao Wang
| Challenge: | Multimodal Large Language Models have shown significant promise in various applications, but a comprehensive evaluation of their long-context capabilities remains underexplored. |
| Approach: | They propose a benchmark to assess the long-context capabilities of multimodal large language models. |
| Outcome: | The proposed benchmark compared MLLMs with API-based and open-source models in a long-context scenario. |
Chain-of-Thought Matters: Improving Long-Context Language Models with Reasoning Path Supervision (2025.findings-emnlp)
Copied to clipboard
Dawei Zhu, Xiyu Wei, Guangxiang Zhao, Wenhao Wu, Haosheng Zou, Junfeng Ran, null XWang, Lin Sun, Xiangzheng Zhang, Sujian Li
| Challenge: | Recent advances in Large Language Models (LLMs) have highlighted the challenge of handling long-context tasks. |
| Approach: | They propose a chain-of-thought framework that teaches models to generate high-quality reasoning paths for enhanced long-context performance. |
| Outcome: | The proposed framework generalizes across most long-context scenarios and amplifys with increasing context length. |
LongReward: Improving Long-context Large Language Models with AI Feedback (2025.acl-long)
Copied to clipboard
Jiajie Zhang, Zhongni Hou, Xin Lv, Shulin Cao, Zhenyu Hou, Yilin Niu, Lei Hou, Yuxiao Dong, Ling Feng, Juanzi Li
| Challenge: | In recent years, significant advancements have been achieved in the development of long-context large language models (LLMs). |
| Approach: | They propose a method that utilizes an off-the-shelf LLM to provide rewards for long-context model responses from four human-valued dimensions: helpfulness, logicality, faithfulness, and completeness. |
| Outcome: | The proposed method improves models’ long-context performance and enhances their ability to follow short instructions. |
Counting-Stars: A Multi-evidence, Position-aware, and Scalable Benchmark for Evaluating Long-Context Large Language Models (2025.coling-main)
Copied to clipboard
| Challenge: | Existing benchmarks for long-context language models have lagged behind . however, there is still room for improvement as the context window and complexity of the tasks increase. |
| Approach: | They propose a long-context benchmark to evaluate the performance of long-text language models. |
| Outcome: | The proposed benchmarks show that the models perform better in long-context environments as the context window increases and complexity increases. |
Cost-Optimal Grouped-Query Attention for Long-Context Modeling (2025.emnlp-main)
Copied to clipboard
Yingfa Chen, Yutong Wu, Chenyang Song, Zhen Leng Thai, Xingyu Shen, Xu Han, Zhiyuan Liu, Maosong Sun
| Challenge: | Current GQA configurations overlook how context length influences inference cost . |
| Approach: | They propose a recipe for deriving cost-optimal GQA configurations that decouple the total head size from the hidden size and allow more flexible control over attention FLOPs. |
| Outcome: | The proposed configurations reduce memory usage and FLOPs by more than 50% compared to Llama-3's GQA, with *no degradation in model capabilities*. |
ARK: Answer-Centric Retriever Tuning via KG-augmented Curriculum Learning (2026.acl-long)
Copied to clipboard
| Challenge: | Retrieval-Augmented Generation (RAG) is a powerful framework for knowledge-intensive tasks, but its effectiveness in long-context scenarios is often bottlenecked by the retriever’s inability to distinguish sparse yet crucial evidence. |
| Approach: | They propose a framework that fine-tunes the retriever for Answer Alignment by identifying high-quality positive chunks by evaluating their sufficiency to generate the correct answer. |
| Outcome: | The proposed framework improves 14.5% over the base model and maintains strong efficiency for long-context RAG. |
QiMeng-Attention: SOTA Attention Operator is generated by SOTA Attention Algorithm (2025.findings-acl)
Copied to clipboard
Qirui Zhou, Shaohui Peng, Weiqiang Xiong, Haixin Chen, Yuanbo Wen, Haochen Li, Ling Li, Qi Guo, Yongwei Zhao, Ke Gao, Ruizhi Chen, Yanjun Wu, Zhao Chen, Yunji Chen
| Challenge: | Existing LLMs cannot comprehend the complex data flow and computation process of the attention operator and utilize low-level primitive to exploit GPU performance. |
| Approach: | They propose an LLM-friendly Thinking Language (LLM-TL) that can decouple the generation of high-level optimization logic and low-level implementation on GPU and enhance LLMs’ understanding of attention operator. |
| Outcome: | The proposed method outshines existing LLMs on A100, RTX8000, and T4 GPUs, achieving a speed-up of up to 35.16. |
TokenSelect: Efficient Long-Context Inference and Length Extrapolation for LLMs via Dynamic Token-Level KV Cache Selection (2025.emnlp-main)
Copied to clipboard
| Challenge: | Rapid advances in Large Language Models have spurred demand for processing extended context sequences . however, performance degradation due to sequence lengths out-of-distribution and excessively long inference times are limiting LLMs in long-context scenarios. |
| Approach: | They propose a training-free method for efficient and accurate long-context inference . they selectively involves a few critical KV cache tokens in attention calculation . |
| Outcome: | The proposed method speeds up attention computation and accelerates inference time while reducing selection overhead. |
Incentivizing In-depth Reasoning over Long Contexts with Process Advantage Shaping (2026.findings-acl)
Copied to clipboard
| Challenge: | Reinforcement Learning with Verifiable Rewards (RLVR) has proven effective in enhancing LLMs’ short-context reasoning but falters in long-contemporal scenarios requiring precise grounding and multi-hop reasoning. |
| Approach: | They propose a framework that constructs high-difficulty, multi-hop long-context QA pairs with inherent reasoning chains to overcome this bottleneck. |
| Outcome: | The proposed framework outperforms RLVR baselines and matches frontier LLMs while using far fewer parameters. |
LongSafety: Evaluating Long-Context Safety of Large Language Models (2025.acl-long)
Copied to clipboard
Yida Lu, Jiale Cheng, Zhexin Zhang, Shiyao Cui, Cunxiang Wang, Xiaotao Gu, Yuxiao Dong, Jie Tang, Hongning Wang, Minlie Huang
| Challenge: | Large Language Models (LLMs) have demonstrated remarkable capabilities in understanding and generating long sequences. |
| Approach: | They propose a benchmark to evaluate LLM safety in open-ended long-context tasks . they find that relevant context and extended input sequences can exacerbate safety risks . |
| Outcome: | The proposed benchmark identifies significant safety vulnerabilities in 16 LLMs . strong safety performance in short-context scenarios does not correlate with safety in long-contact tasks . |