English
Related papers

Related papers: Characterizing Paraphrase-Induced Failures in Lean…

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

While Large Language Models (LLMs) are widely documented to be sensitive to minor prompt perturbations and prone to sycophantic alignment, their robustness in consequential, rule-bound decision-making remains under-explored. We uncover a…

Artificial Intelligence · Computer Science 2026-04-07 Jon Chun , Katherine Elkins

Training models on synthetic data has emerged as an increasingly important strategy for improving the performance of generative AI. This approach is particularly helpful for large multimodal models (LMMs) due to the relative scarcity of…

Artificial Intelligence · Computer Science 2026-01-13 Gabriela Ben Melech Stan , Estelle Aflalo , Avinash Madasu , Vasudev Lal , Phillip Howard

Insensitivity to semantically-preserving variations of prompts (paraphrases) is crucial for reliable behavior and real-world deployment of large language models. However, language models exhibit significant performance degradation when…

Computation and Language · Computer Science 2025-03-04 Tingchen Fu , Fazl Barez

Large language models trained under diverse objectives and architectures have been shown to develop increasingly similar internal representations, an observation formalized as the Platonic Representation Hypothesis. Whether this…

Computation and Language · Computer Science 2026-05-25 Muhammad Usama , Dong Eui Chang

Large language models excel on math benchmarks, but their math reasoning robustness to linguistic variation is underexplored. While recent work increasingly treats high-difficulty competitions like the IMO as the gold standard for…

Computation and Language · Computer Science 2025-10-09 Neeraja Kirtane , Yuvraj Khanna , Peter Relan

Although large language models (LLMs) have transformed AI, they still make mistakes and can explore unproductive reasoning paths. Self-correction capability is essential for deploying LLMs in safety-critical applications. We uncover a…

Computation and Language · Computer Science 2025-10-07 Ken Tsui

Large language models have demonstrated impressive performance across many domains of mathematics and physics. One natural question is whether such models can support research in highly abstract theoretical fields such as quantum field…

Computational Physics · Physics 2026-04-17 Xingyang Yu , Yinghuan Zhang , Yufei Zhang , Zijun Cui

Large language models (LLMs) are being rapidly integrated into decision-support tools, automation workflows, and AI-enabled software systems. However, their behavior in production environments remains poorly understood, and their failure…

Artificial Intelligence · Computer Science 2025-11-27 Vaishali Vinay

Translating natural language into formal language such as First-Order Logic (FOL) is a foundational challenge in NLP with wide-ranging applications in automated reasoning, misinformation tracking, and knowledge validation. In this paper, we…

Computation and Language · Computer Science 2025-03-07 Abhinav Lalwani , Tasha Kim , Lovish Chopra , Christopher Hahn , Zhijing Jin , Mrinmaya Sachan

There has been considerable divergence of opinion on the reasoning abilities of Large Language Models (LLMs). While the initial optimism that reasoning might emerge automatically with scale has been tempered thanks to a slew of…

Artificial Intelligence · Computer Science 2024-08-06 Kaya Stechly , Karthik Valmeekam , Subbarao Kambhampati

Large language models (LLMs) demonstrate remarkable reasoning capabilities, yet their performance often deteriorates sharply in long-horizon tasks, exhibiting systematic breakdown beyond certain scales. Conventional explanations primarily…

Artificial Intelligence · Computer Science 2026-02-09 Hsien-Jyh Liao

While AI-generated text (AIGT) detectors achieve over 90\% accuracy on direct LLM outputs, they fail catastrophically against iteratively-paraphrased content. We investigate why iteratively-paraphrased text -- itself AI-generated -- evades…

Computation and Language · Computer Science 2025-11-04 Yiwei Zha , Rui Min , Shanu Sushmita

Automated formalization of mathematics enables mechanical verification but remains limited to isolated theorems and short snippets. Scaling to textbooks and research papers is largely unaddressed, as it requires managing cross-file…

Artificial Intelligence · Computer Science 2026-02-20 Zichen Wang , Wanli Ma , Zhenyu Ming , Gong Zhang , Kun Yuan , Zaiwen Wen

The impressive performance of Large Language Models (LLMs) has consistently surpassed numerous human-designed benchmarks, presenting new challenges in assessing the shortcomings of LLMs. Designing tasks and finding LLMs' limitations are…

Computation and Language · Computer Science 2024-10-02 Yulong Chen , Yang Liu , Jianhao Yan , Xuefeng Bai , Ming Zhong , Yinghao Yang , Ziyi Yang , Chenguang Zhu , Yue Zhang

Despite significant advances in alignment techniques, we demonstrate that state-of-the-art language models remain vulnerable to carefully crafted conversational scenarios that can induce various forms of misalignment without explicit…

Computation and Language · Computer Science 2025-08-07 Siddhant Panpatil , Hiskias Dingeto , Haon Park

The burgeoning computational demands for training large language models (LLMs) necessitate efficient methods, including quantized training, which leverages low-bit arithmetic operations to reduce costs. While FP8 precision has shown…

Machine Learning · Computer Science 2025-02-18 Jiecheng Zhou , Ding Tang , Rong Fu , Boni Hu , Haoran Xu , Yi Wang , Zhilin Pei , Zhongling Su , Liang Liu , Xingcheng Zhang , Weiming Zhang

In various fields of knowledge creation, including science, new ideas often build on pre-existing information. In this work, we explore this concept within the context of language models. Specifically, we explore the potential of…

Computation and Language · Computer Science 2024-04-04 David Herel , Tomas Mikolov

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

We present an autoformalisation framework for the Lean theorem prover, called GFLean. GFLean uses a high-level grammar writing tool called Grammatical Framework (GF) for parsing and linearisation. GFLean is implemented in Haskell. We…

Computation and Language · Computer Science 2024-04-02 Shashank Pathak