English
Related papers

Related papers: Positional Failures in Long-Context LLMs: A Blind …

200 papers

The needle-in-a-haystack (NIAH) test, which examines the ability to retrieve a piece of information (the "needle") from long distractor texts (the "haystack"), has been widely adopted to evaluate long-context language models (LMs). However,…

Computation and Language · Computer Science 2024-08-08 Cheng-Ping Hsieh , Simeng Sun , Samuel Kriman , Shantanu Acharya , Dima Rekesh , Fei Jia , Yang Zhang , Boris Ginsburg

Recent large language models (LLMs) support long contexts ranging from 128K to 1M tokens. A popular method for evaluating these capabilities is the needle-in-a-haystack (NIAH) test, which involves retrieving a "needle" (relevant…

Computation and Language · Computer Science 2025-07-10 Ali Modarressi , Hanieh Deilamsalehy , Franck Dernoncourt , Trung Bui , Ryan A. Rossi , Seunghyun Yoon , Hinrich Schütze

This study investigates the reasoning robustness of large language models (LLMs) on mathematical problem-solving tasks under systematically introduced input perturbations. Using the GSM8K dataset as a controlled testbed, we evaluate how…

Artificial Intelligence · Computer Science 2025-04-04 Giannis Chatziveroglou , Richard Yun , Maura Kelleher

Embedding models play a pivot role in modern NLP applications such as IR and RAG. While the context limit of LLMs has been pushed beyond 1 million tokens, embedding models are still confined to a narrow context window not exceeding 8k…

Computation and Language · Computer Science 2024-11-08 Dawei Zhu , Liang Wang , Nan Yang , Yifan Song , Wenhao Wu , Furu Wei , Sujian Li

Existing multilingual long-context benchmarks, often based on the popular needle-in-a-haystack test, primarily evaluate a model's ability to locate specific information buried within irrelevant texts. However, such a retrieval-centric…

Computation and Language · Computer Science 2025-04-18 Amey Hengle , Prasoon Bajpai , Soham Dan , Tanmoy Chakraborty

Many benchmarks exist for evaluating long-context language models (LCLMs), yet developers often rely on synthetic tasks such as needle-in-a-haystack (NIAH) or an arbitrary subset of tasks. However, it remains unclear whether these…

Computation and Language · Computer Science 2025-03-07 Howard Yen , Tianyu Gao , Minmin Hou , Ke Ding , Daniel Fleischer , Peter Izsak , Moshe Wasserblat , Danqi Chen

Advancements in distributed training and efficient attention mechanisms have significantly expanded the context window sizes of large language models (LLMs). However, recent work reveals that the effective context lengths of open-source…

Computation and Language · Computer Science 2024-10-25 Chenxin An , Jun Zhang , Ming Zhong , Lei Li , Shansan Gong , Yao Luo , Jingjing Xu , Lingpeng Kong

Large language models (LLMs) have demonstrated remarkable progress in understanding long-context inputs. However, benchmarks for evaluating the long-context reasoning abilities of LLMs fall behind the pace. Existing benchmarks often focus…

Computation and Language · Computer Science 2025-11-19 Zhan Ling , Kang Liu , Kai Yan , Yifan Yang , Weijian Lin , Ting-Han Fan , Lingfeng Shen , Zhengyin Du , Jiecao Chen

Long-context capability is considered one of the most important abilities of LLMs, as a truly long context-capable LLM enables users to effortlessly process many originally exhausting tasks -- e.g., digesting a long-form document to find…

Computation and Language · Computer Science 2025-05-27 Wang Yang , Hongye Jin , Shaochen Zhong , Song Jiang , Qifan Wang , Vipin Chaudhary , Xiaotian Han

Recent large language models (LLMs) have demonstrated versatile capabilities in long-context scenarios. Although some recent benchmarks have been developed to evaluate the long-context capabilities of LLMs, there is a lack of benchmarks…

Computation and Language · Computer Science 2024-10-08 Lei Wang , Shan Dong , Yuhui Xu , Hanze Dong , Yalu Wang , Amrita Saha , Ee-Peng Lim , Caiming Xiong , Doyen Sahoo

While Large Language Models (LLMs) achieve high performance on standard mathematical benchmarks, their problem-solving abilities depend on the context and textual formatting. We introduce the Robust Reasoning Benchmark (RRB), a pipeline of…

Machine Learning · Computer Science 2026-05-22 Pavel Golikov , Evgenii Opryshko , Gennady Pekhimenko , Mark C. Jeffrey

Long-context adaptation is often viewed as window scaling, but this misses a token-level supervision mismatch: in packed training with document masking, each target token's effective context remains short. We introduce EXACT, a…

Computation and Language · Computer Science 2026-05-12 Jinchang Zhu , Jindong Li , Chengyu Zou , Rong Fu , Chao Wang , Haowei He , Menglin Yang

Large language models (LLMs) exhibiting test-time scaling behavior, such as extended reasoning traces and self-verification, have demonstrated remarkable performance on complex, long-term reasoning tasks. However, the robustness of these…

Machine Learning · Computer Science 2026-04-02 Gleb Rodionov

LongRoPE2 is a novel approach that extends the effective context window of pre-trained large language models (LLMs) to the target length, while preserving the performance on the original shorter context window. This is achieved by three…

Computation and Language · Computer Science 2025-02-28 Ning Shang , Li Lyna Zhang , Siyuan Wang , Gaokai Zhang , Gilsinia Lopez , Fan Yang , Weizhu Chen , Mao Yang

Large language models (LLMs) often fail to scale their performance on long-context tasks performance in line with the context lengths they support. This gap is commonly attributed to retrieval failures -- the models' inability to identify…

Computation and Language · Computer Science 2025-10-08 Yufeng Du , Minyang Tian , Srikanth Ronanki , Subendhu Rongali , Sravan Bodapati , Aram Galstyan , Azton Wells , Roy Schwartz , Eliu A Huerta , Hao Peng

Large language models (LLMs) increasingly support very long input contexts. Yet it remains unclear how reliably they extract and infer information at scale. Performance varies with context length and strongly interacts with how information…

Computation and Language · Computer Science 2026-01-06 Amirali Ebrahimzadeh , Seyyed M. Salili

The ability to recognize patterns from examples and apply them to new ones is a primal ability for general intelligence, and is widely studied by psychology and AI researchers. Many benchmarks have been proposed to measure such ability for…

Artificial Intelligence · Computer Science 2025-10-24 Kai Yan , Zhan Ling , Kang Liu , Yifan Yang , Ting-Han Fan , Lingfeng Shen , Zhengyin Du , Jiecao Chen

The long-context capabilities of large language models (LLMs) have been a hot topic in recent years. To evaluate the performance of LLMs in different scenarios, various assessment benchmarks have emerged. However, as most of these…

Computation and Language · Computer Science 2025-08-14 Shawn Gavin , Tuney Zheng , Jiaheng Liu , Quehry Que , Noah Wang , Jian Yang , Chenchen Zhang , Wenhao Huang , Ge Zhang

State-of-the-art large language models (LLMs) are now claiming remarkable supported context lengths of 256k or even more. In contrast, the average context lengths of mainstream benchmarks are insufficient (5k-21k), and they suffer from…

Computation and Language · Computer Science 2025-10-23 Tao Yuan , Xuefei Ning , Dong Zhou , Zhijie Yang , Shiyao Li , Minghui Zhuang , Zheyue Tan , Zhuyu Yao , Dahua Lin , Boxun Li , Guohao Dai , Shengen Yan , Yu Wang

Large language models (LLMs) are increasingly capable of carrying out long-running, real-world tasks. However, as the amount of context grows, their reliability often deteriorates, a phenomenon known as "context rot". Existing long-context…

Artificial Intelligence · Computer Science 2026-02-10 Weihao Zeng , Yuzhen Huang , Junxian He
‹ Prev 1 2 3 10 Next ›