English
Related papers

Related papers: MathGAP: Out-of-Distribution Evaluation on Problem…

200 papers

Comprehensive evaluation of Large Language Models (LLMs) is an open research problem. Existing evaluations rely on deterministic point estimates generated via greedy decoding. However, we find that deterministic evaluations fail to capture…

Machine Learning · Computer Science 2025-03-04 Yan Scholten , Stephan Günnemann , Leo Schwinn

Large language models (LLMs) have achieved substantial progress in processing long contexts but still struggle with long-context reasoning. Existing approaches typically involve fine-tuning LLMs with synthetic data, which depends on…

Computation and Language · Computer Science 2024-11-14 Siheng Li , Cheng Yang , Zesen Cheng , Lemao Liu , Mo Yu , Yujiu Yang , Wai Lam

Evaluations of large language models (LLMs) primarily emphasize convergent logical reasoning, where success is defined by producing a single correct proof. However, many real-world reasoning problems admit multiple valid derivations,…

Artificial Intelligence · Computer Science 2026-02-25 Yanrui Wu , Lingling Zhang , Xinyu Zhang , Jiayu Chang , Pengyu Li , Xu Jiang , Jingtao Hu , Jun Liu

Large language models (LLMs) increasingly excel at mathematical reasoning, but their unreliability limits their utility in mathematics research. A mitigation is using LLMs to generate formal proofs in languages like Lean. We perform the…

Current LLM training positions mathematical reasoning as a core capability. With publicly available sources fully tapped, there is unmet demand for diverse and challenging math questions. Relying solely on human experts is both…

Artificial Intelligence · Computer Science 2025-02-04 Vedant Shah , Dingli Yu , Kaifeng Lyu , Simon Park , Jiatong Yu , Yinghui He , Nan Rosemary Ke , Michael Mozer , Yoshua Bengio , Sanjeev Arora , Anirudh Goyal

Large language models (LLMs) have achieved remarkable performance in various evaluation benchmarks. However, concerns are raised about potential data contamination in their considerable volume of training corpus. Moreover, the static nature…

Artificial Intelligence · Computer Science 2024-03-15 Kaijie Zhu , Jiaao Chen , Jindong Wang , Neil Zhenqiang Gong , Diyi Yang , Xing Xie

Machine learning approaches applied to NLP are often evaluated by summarizing their performance in a single number, for example accuracy. Since most test sets are constructed as an i.i.d. sample from the overall data, this approach overly…

Given the emergent reasoning abilities of large language models, information retrieval is becoming more complex. Rather than just retrieve a document, modern information retrieval systems advertise that they can synthesize an answer based…

Information Retrieval · Computer Science 2024-03-15 Gregory Coppola

Large language models (LLMs) have achieved remarkable success across various natural language processing (NLP) tasks. However, recent studies suggest that they still face challenges in performing fundamental NLP tasks essential for deep…

Computation and Language · Computer Science 2025-04-22 Ziyan Zhang , Yang Hou , Chen Gong , Zhenghua Li

Large language models exhibit a puzzling inconsistency: they solve complex problems yet frequently fail on seemingly simpler ones. We investigate whether LLMs internally encode problem difficulty in a way that aligns with human judgment,…

Computation and Language · Computer Science 2025-10-22 William Lugoloobi , Chris Russell

Large language models (LLMs) have seen considerable advancements in natural language understanding tasks, yet there remains a gap to bridge before attaining true artificial general intelligence, especially concerning shortcomings in…

Computation and Language · Computer Science 2024-02-23 Minpeng Liao , Wei Luo , Chengxi Li , Jing Wu , Kai Fan

Ensuring the reliability and verifiability of large language model (LLM)-enabled systems remains a significant challenge in software engineering. We propose a probabilistic framework for systematically analyzing and improving these systems…

Software Engineering · Computer Science 2025-04-15 Juan Manuel Baldonado , Flavia Bonomo-Braberman , Víctor Adrián Braberman

Large language models (LLMs) have demonstrated remarkable reasoning capability in solving mathematical problems. However, existing approaches primarily focus on improving the quality of correct training data, e.g., distilling high-quality…

Machine Learning · Computer Science 2025-06-02 Zhuoshi Pan , Yu Li , Honglin Lin , Qizhi Pei , Zinan Tang , Wei Wu , Chenlin Ming , H. Vicky Zhao , Conghui He , Lijun Wu

Large Language Models (LLMs) have been touted as AI models possessing advanced reasoning abilities. However, recent works have shown that LLMs often bypass true reasoning using shortcuts, sparking skepticism. To study the reasoning…

Artificial Intelligence · Computer Science 2024-10-24 Rishi Hazra , Gabriele Venturato , Pedro Zuidberg Dos Martires , Luc De Raedt

Large Language Models (LLMs) have demonstrated strong performance across a wide range of tasks, yet they still struggle with complex mathematical reasoning, a challenge fundamentally rooted in deep structural dependencies. To address this…

Artificial Intelligence · Computer Science 2025-12-01 Lei Zan , Keli Zhang , Ruichu Cai , Lujia Pan

Large Language Models (LLMs) have demonstrated strong capabilities across diverse NLP applications, such as translation, text generation, and question answering. Nevertheless, they remain limited in complex settings that demand deep…

Computation and Language · Computer Science 2026-05-18 Xin Zhang , Yang Cao , Baoxing Wu , Kai Song , Siying Li

With the recent undeniable advancement in reasoning abilities in large language models (LLMs) like ChatGPT and GPT-4, there is a growing trend for using LLMs on various tasks. One area where LLMs can be employed is as an alternative…

Computation and Language · Computer Science 2023-10-23 Chenhui Shen , Liying Cheng , Xuan-Phi Nguyen , Yang You , Lidong Bing

Large Language Models (LLMs) are often used as automated judges to evaluate text, but their effectiveness can be hindered by various unintentional biases. We propose using linear classifying probes, trained by leveraging differences between…

Computation and Language · Computer Science 2025-03-25 Sharan Maiya , Yinhong Liu , Ramit Debnath , Anna Korhonen

The evaluation of mathematical reasoning capabilities is essential for advancing Artificial General Intelligence (AGI). While Large Language Models (LLMs) have shown impressive performance in solving mathematical problems, existing…

Computation and Language · Computer Science 2025-01-15 Bo Yang , Qingping Yang , Yingwei Ma , Runtao Liu

Large Language Models (LLMs) have exhibited an impressive capability to perform reasoning tasks, especially if they are encouraged to generate a sequence of intermediate steps. Reasoning performance can be improved by suitably combining…

Computation and Language · Computer Science 2025-04-11 Soumyasundar Pal , Didier Chételat , Yingxue Zhang , Mark Coates