English
Related papers

Related papers: The Perplexity Paradox: Why Code Compresses Better…

200 papers

This paper focuses on task-agnostic prompt compression for better generalizability and efficiency. Considering the redundancy in natural language, existing approaches compress prompts by removing tokens or lexical units according to their…

Reliable evaluation protocols are of utmost importance for reproducible NLP research. In this work, we show that sometimes neither metric nor conventional human evaluation is sufficient to draw conclusions about system performance. Using…

Computation and Language · Computer Science 2021-01-25 Yevgeniy Puzikov

Despite the recent success of large language models (LLMs) in reasoning such as DeepSeek, we for the first time identify a key dilemma in reasoning robustness and generalization: significant performance degradation on novel or incomplete…

Artificial Intelligence · Computer Science 2025-03-07 Tong Yu , Yongcheng Jing , Xikun Zhang , Wentao Jiang , Wenjie Wu , Yingjie Wang , Wenbin Hu , Bo Du , Dacheng Tao

A range of recent works addresses the problem of compression of sequence of tokens into a shorter sequence of real-valued vectors to be used as inputs instead of token embeddings or key-value cache. These approaches are focused on reduction…

Computation and Language · Computer Science 2025-06-24 Yuri Kuratov , Mikhail Arkhipov , Aydar Bulatov , Mikhail Burtsev

Large reasoning models (LRMs) excel on complex problems but face a critical barrier to efficiency: reinforcement learning (RL) training requires long rollouts for outcome-based rewards, where autoregressive decoding dominates time and…

Machine Learning · Computer Science 2026-02-20 Zeliang Zhang , Xiaodong Liu , Hao Cheng , Hao Sun , Chenliang Xu , Jianfeng Gao

Large Language Models (LLMs) have demonstrated impressive capabilities in reasoning using Chain-of-Thought (CoT) prompting. However, CoT can be biased by users' instruction. In this work, we study the reasoning robustness of LLMs to…

Computation and Language · Computer Science 2024-11-11 Esther Gan , Yiran Zhao , Liying Cheng , Yancan Mao , Anirudh Goyal , Kenji Kawaguchi , Min-Yen Kan , Michael Shieh

Code snippet adaptation is a fundamental activity in the software development process. Unlike code generation, code snippet adaptation is not a "free creation", which requires developers to tailor a given code snippet in order to fit…

Software Engineering · Computer Science 2024-11-26 Tanghaoran Zhang , Yue Yu , Xinjun Mao , Shangwen Wang , Kang Yang , Yao Lu , Zhang Zhang , Yuxin Zhao

Recent advances in reasoning with large language models (LLMs) have demonstrated strong performance on complex mathematical tasks, including combinatorial optimization. Techniques such as Chain-of-Thought and In-Context Learning have…

Artificial Intelligence · Computer Science 2025-09-17 Marylou Fauchard , Florian Carichon , Margarida Carvalho , Golnoosh Farnadi

Long chains of thought (Long CoTs) are widely employed in multimodal reasoning models to tackle complex tasks by capturing detailed visual information. However, these Long CoTs are often excessively lengthy and contain redundant reasoning…

Artificial Intelligence · Computer Science 2026-02-11 Yizhi Wang , Linan Yue , Min-Ling Zhang

Large language models (LLMs) exhibit degraded performance under prompt compression, but the mechanisms remain poorly understood. We introduce the Compression-Decay Comprehension Test (CDCT), a benchmark that independently measures…

Computation and Language · Computer Science 2025-12-23 Rahul Baxi

Image coding for machines (ICM) aims to compress images to support downstream AI analysis instead of human perception. For ICM, developing a unified codec to reduce information redundancy while empowering the compressed features to support…

Computer Vision and Pattern Recognition · Computer Science 2023-05-05 Ruoyu Feng , Jinming Liu , Xin Jin , Xiaohan Pan , Heming Sun , Zhibo Chen

Enhancing reasoning capabilities remains a central focus in the LLM reasearch community. A promising direction involves requiring models to simulate code execution step-by-step to derive outputs for given inputs. However, as code is often…

Computation and Language · Computer Science 2025-07-15 Keqin Bao , Nuo Chen , Xiaoyuan Li , Binyuan Hui , Bowen Yu , Fuli Feng , Xiangnan He , Dayiheng Liu

Scaling test-time compute via Long Chain-of-Thought (Long-CoT) significantly enhances reasoning capabilities, yet extended generation does not guarantee correctness: after an early wrong commitment, models may keep elaborating a…

Artificial Intelligence · Computer Science 2026-01-21 Kang Chen , Fan Yu , Junjie Nian , Shihan Zhao , Zhuoka Feng , Zijun Yao , Heng Wang , Minshen Yu , Yixin Cao

Increasingly, model compression techniques enable large language models (LLMs) to be deployed in real-world applications. As a result of this momentum towards local deployment, compressed LLMs will interact with a large population. Prior…

Computation and Language · Computer Science 2024-10-15 Zhichao Xu , Ashim Gupta , Tao Li , Oliver Bentham , Vivek Srikumar

Mathematical Word Problems (MWPs) are among the most challenging tasks in natural language processing because they require both linguistic understanding and multi-step numerical reasoning. While Chain-of-Thought (CoT) prompting has shown…

Computation and Language · Computer Science 2025-12-08 Aurprita Mahmood , Sabrin alam , Neloy kumer Sagor , Md. Abdul Hadi , Md. Sehab Al Islam , Minhajul Islam

Transformer-based language models for code have shown remarkable performance in various software analytics tasks, but their adoption is hindered by high computational costs, slow inference speeds, and substantial environmental impact. Model…

Software Engineering · Computer Science 2026-04-15 Md. Abdul Awal , Mrigank Rochan , Chanchal K. Roy

Prompt programming treats large language model prompts as software components with typed interfaces. Based on a literature survey of 15 recent works from 2023 to 2025, we observe a consistent trend: type systems are central to emerging…

Programming Languages · Computer Science 2025-08-19 Abhijit Paul

Human cognition typically involves thinking through abstract, fluid concepts rather than strictly using discrete linguistic tokens. Current reasoning models, however, are constrained to reasoning within the boundaries of human language,…

Computation and Language · Computer Science 2025-05-22 Zhen Zhang , Xuehai He , Weixiang Yan , Ao Shen , Chenyang Zhao , Shuohang Wang , Yelong Shen , Xin Eric Wang

Large language models (LLMs), despite their impressive performance across a wide range of tasks, often struggle to balance two competing objectives in open-ended text generation: fostering diversity and creativity while preserving logical…

Computation and Language · Computer Science 2026-05-12 Erfan Baghaei Potraghloo , Seyedarmin Azizi , Souvik Kundu , Massoud Pedram

Prompt sensitivity, referring to the phenomenon where paraphrasing (i.e., repeating something written or spoken using different words) leads to significant changes in large language model (LLM) performance, has been widely accepted as a…

Computation and Language · Computer Science 2025-09-03 Andong Hua , Kenan Tang , Chenhe Gu , Jindong Gu , Eric Wong , Yao Qin