English
Related papers

Related papers: Why Retrying Fails: Context Contamination in LLM A…

200 papers

Large Language Models (LLMs) excel at single-turn tasks such as instruction following and summarization, yet real-world deployments require sustained multi-turn interactions where user goals and conversational context persist and evolve. A…

Computation and Language · Computer Science 2025-11-25 Vardhan Dongre , Ryan A. Rossi , Viet Dac Lai , David Seunghyun Yoon , Dilek Hakkani-Tür , Trung Bui

Large reasoning models (LRMs) typically solve reasoning-intensive tasks by generating long chain-of-thought (CoT) traces, leading to substantial inference overhead. We identify a reproducible inference-time phenomenon, termed…

Computation and Language · Computer Science 2026-02-03 Jie Deng , Shining Liang , Jun Li , Hongzhi Li , Yutao Xie

Retrieval-augmented language models (RALMs) hold promise to produce language understanding systems that are are factual, efficient, and up-to-date. An important desideratum of RALMs, is that retrieved information helps model performance…

Computation and Language · Computer Science 2024-05-07 Ori Yoran , Tomer Wolfson , Ori Ram , Jonathan Berant

Parameter-efficient methods are able to use a single frozen pre-trained large language model (LLM) to perform many tasks by learning task-specific soft prompts that modulate model behavior when concatenated to the input text. However, these…

Computation and Language · Computer Science 2022-08-12 Brian Lester , Joshua Yurtsever , Siamak Shakeri , Noah Constant

The development of Long-Context Large Language Models (LLMs) has markedly advanced natural language processing by facilitating the process of textual data across long documents and multiple corpora. However, Long-Context LLMs still face two…

Computation and Language · Computer Science 2024-10-10 Jingyang Deng , Zhengyang Shen , Boyang Wang , Lixin Su , Suqi Cheng , Ying Nie , Junfeng Wang , Dawei Yin , Jinwen Ma

Identifying subtle technical errors within complex scientific and technical documents, especially those requiring multimodal interpretation (e.g., formulas in images), presents a significant hurdle for Large Language Models (LLMs) whose…

Computers and Society · Computer Science 2025-05-21 Evgeny Markhasin

Multi-turn dialogues and context-intensive tasks challenge Large Language Models (LLMs) to integrate long histories without sacrificing generation quality. Although prefix LLMs can better exploit historical context via bidirectional…

Computation and Language · Computer Science 2026-02-18 HaoYuan Hu , Mingcong Lu , Di Luo , XinYa Wu , Jiangcai Zhu , Taoye Yin , Zheng Li , Hao Wang , Shusheng Zhang , KeZun Zhang , KaiLai Shao , Chao Chen , Feng Wang

The remarkable performance of pre-trained large language models has revolutionised various natural language processing applications. Due to huge parametersizes and extensive running costs, companies or organisations tend to transfer the…

Computation and Language · Computer Science 2023-12-15 Jiazheng Li , Runcong Zhao , Yongxin Yang , Yulan He , Lin Gui

The performance of Large Language Models (LLMs) is fundamentally determined by the contextual information provided during inference. This survey introduces Context Engineering, a formal discipline that transcends simple prompt design to…

Generative LLM have achieved remarkable success in various industrial applications, owing to their promising In-Context Learning capabilities. However, the issue of long context in complex tasks poses a significant barrier to their wider…

Computation and Language · Computer Science 2025-10-14 Yihang Wang , Xu Huang , Bowen Tian , Yueyang Su , Lei Yu , Huaming Liao , Yixing Fan , Jiafeng Guo , Xueqi Cheng

Language Model (LM) pipelines can dynamically refine their outputs against programmatic constraints. However, their effectiveness collapses when faced with competing soft constraints, leading to inefficient backtracking loops where…

Software Engineering · Computer Science 2025-07-16 Mojtaba Eshghie

Transformers suffer from a high computational cost that grows with sequence length for self-attention, making inference in long streams prohibited by memory consumption. Constant-memory alternatives such as RNNs and SSMs compress history…

Machine Learning · Computer Science 2026-04-24 Zhixin Zhang , Shabo Zhang , Chengcan Wu , Zeming Wei , Meng Sun

Large Language Models (LLMs) have demonstrated success across many benchmarks. However, they still exhibit limitations in long-context scenarios, primarily due to their short effective context length, quadratic computational complexity, and…

Computation and Language · Computer Science 2025-09-26 Manlai Liang , Mandi Liu , Jiangzhou Ji , Huaijun Li , Haobo Yang , Yaohan He , Jinlong Li

While Multimodal Large Language Models (MLLMs) are increasingly integrated with Retrieval-Augmented Generation (RAG) to mitigate hallucinations, the introduction of external documents can conceal severe failure modes at the instance level.…

Computation and Language · Computer Science 2026-05-08 Hoin Jung , Xiaoqian Wang

The accelerating adoption of language models (LMs) as agents for deployment in long-context tasks motivates a thorough understanding of goal drift: agents' tendency to deviate from an original objective. While prior-generation language…

Artificial Intelligence · Computer Science 2026-03-04 Achyutha Menon , Magnus Saebo , Tyler Crosse , Spencer Gibson , Eyon Jang , Diogo Cruz

Existing benchmarks for tool-augmented language models (TaLMs) lack fine-grained control over task difficulty and remain vulnerable to data contamination. We present FuncBenchGen, a unified, contamination-free framework that evaluates TaLMs…

Computation and Language · Computer Science 2026-02-10 Seiji Maekawa , Jackson Hassell , Pouya Pezeshkpour , Tom Mitchell , Estevam Hruschka

Safety alignment approaches in large language models (LLMs) often lead to the over-refusal of benign queries, significantly diminishing their utility in sensitive scenarios. To address this challenge, we introduce FalseReject, a…

Computation and Language · Computer Science 2025-07-16 Zhehao Zhang , Weijie Xu , Fanyou Wu , Chandan K. Reddy

Existing Large Language Model (LLM) benchmarks primarily focus on syntactically correct inputs, leaving a significant gap in evaluation on imperfect text. In this work, we study how word-boundary corruption affects how LLMs detect targeted…

Computation and Language · Computer Science 2026-05-11 Zekai Tong , Ruiyao Xu , Aryan Shrivastava , Chenhao Tan , Ari Holtzman

As AI agents powered by large language models (LLMs) increasingly use external tools for high-stakes decisions, a critical reliability question arises: how do errors propagate across sequential tool calls? We introduce the first theoretical…

Artificial Intelligence · Computer Science 2026-02-17 Flint Xiaofeng Fan , Cheston Tan , Roger Wattenhofer , Yew-Soon Ong

Large Language Models employing Chain-of-Thought reasoning achieve strong performance but suffer from excessive token consumption that inflates inference costs. Existing efficiency methods such as explicit length penalties, difficulty…

Machine Learning · Computer Science 2026-04-03 Bangji Yang , Hongbo Ma , Jiajun Fan , Ge Liu