English
Related papers

Related papers: MaP: A Unified Framework for Reliable Evaluation o…

200 papers

In this paper, we study the "stability" of machine learning (ML) models within the context of larger, complex NLP systems with continuous training data updates. For this study, we propose a methodology for the assessment of model stability…

Computation and Language · Computer Science 2022-01-19 Huiting Liu , Avinesh P. V. S. , Siddharth Patwardhan , Peter Grasch , Sachin Agarwal

Reinforcement learning (RL) plays a crucial role in shaping the behavior of large language and reasoning models (LLMs/LRMs). However, it often produces brittle and unstable policies, leading to critical failures such as spurious reasoning,…

Artificial Intelligence · Computer Science 2025-07-29 Xingcheng Xu

Reasoning failures in large language models (LLMs) are typically measured only at the end of a generation, yet many failures manifest as a process-level breakdown: the model "loses the thread" mid-reasoning. We study whether such breakdowns…

Artificial Intelligence · Computer Science 2026-02-04 Jinkun Chen , Fengxiang Cheng , Sijia Han , Vlado Keselj

Unlearning in Large Language Models (LLMs) aims to enhance safety, mitigate biases, and comply with legal mandates, such as the right to be forgotten. However, existing unlearning methods are brittle: minor query modifications, such as…

Artificial Intelligence · Computer Science 2026-03-13 Raj Sanjay Shah , Jing Huang , Keerthiram Murugesan , Nathalie Baracaldo , Diyi Yang

Large language models (LLMs) have shown tremendous success in following user instructions and generating helpful responses. Nevertheless, their robustness is still far from optimal, as they may generate significantly inconsistent responses…

Computation and Language · Computer Science 2024-03-25 Yukun Zhao , Lingyong Yan , Weiwei Sun , Guoliang Xing , Shuaiqiang Wang , Chong Meng , Zhicong Cheng , Zhaochun Ren , Dawei Yin

Though Large Language Models (LLMs) have demonstrated the powerful capabilities of few-shot learning through prompting methods, supervised training is still necessary for complex reasoning tasks. Because of their extensive parameters and…

Computation and Language · Computer Science 2024-06-07 Linhai Zhang , Jialong Wu , Deyu Zhou , Guoqiang Xu

Fine-tuning a pre-trained model (such as BERT, ALBERT, RoBERTa, T5, GPT, etc.) has proven to be one of the most promising paradigms in recent NLP research. However, numerous recent works indicate that fine-tuning suffers from the…

Machine Learning · Computer Science 2023-12-08 Zihao Fu , Anthony Man-Cho So , Nigel Collier

Current techniques for post-training Large Language Models (LLMs) rely either on costly human supervision or on external verifiers to boost performance on tasks such as mathematical reasoning and code generation. However, as LLMs improve…

Computation and Language · Computer Science 2026-01-21 Mukesh Ghimire , Aosong Feng , Liwen You , Youzhi Luo , Fang Liu , Xuan Zhu

Uncovering early-stage metrics that reflect final model performance is one core principle for large-scale pretraining. The existing scaling law demonstrates the power-law correlation between pretraining loss and training flops, which serves…

Evaluation of large language models (LLMs) has raised great concerns in the community due to the issue of data contamination. Existing work designed evaluation protocols using well-defined algorithms for specific tasks, which cannot be…

Computation and Language · Computer Science 2024-06-10 Kaijie Zhu , Jindong Wang , Qinlin Zhao , Ruochen Xu , Xing Xie

Deep learning systems achieve remarkable empirical performance, yet the stability of the training process itself remains poorly understood. Training unfolds as a high-dimensional dynamical system in which small perturbations to…

Machine Learning · Computer Science 2026-01-21 Zhipeng Zhang , Zhenjie Yao , Kai Li , Lei Yang

Despite advances in large language models (LLMs) on reasoning and instruction-following tasks, it is unclear whether they can reliably produce outputs aligned with a variety of user goals, a concept called steerability. Two gaps in current…

Computation and Language · Computer Science 2026-01-21 Trenton Chang , Tobias Schnabel , Adith Swaminathan , Jenna Wiens

Prolonged reinforcement learning with verifiable rewards (RLVR) has been shown to drive continuous improvements in the reasoning capabilities of large language models, but the training is often prone to instabilities, especially in…

Artificial Intelligence · Computer Science 2026-05-13 Yiming Dong , Kun Fu , Haoyu Li , Xinyuan Zhu , Yurou Liu , Lijing Shao , Jieping Ye , Zheng Wang

Large language models (LLMs) demonstrate considerable potential in various natural language tasks but face significant challenges in mathematical reasoning, particularly in executing precise, multi-step logic. However, current evaluation…

Computation and Language · Computer Science 2025-05-22 Tiasa Singha Roy , Aditeya Baral , Ayush Rajesh Jhaveri , Yusuf Baig

Recent advances in reasoning capabilities of large language models (LLMs) are largely driven by reinforcement learning (RL), yet the underlying parameter dynamics during RL training remain poorly understood. This work identifies two…

Machine Learning · Computer Science 2026-02-24 Yuchen Cai , Ding Cao , Xin Xu , Zijun Yao , Yuqing Huang , Zhenyu Tan , Benyi Zhang , Guangzhong Sun , Guiquan Liu , Junfeng Fang

Large Language Models (LLMs) are increasingly deployed in high-stakes contexts where their outputs influence real-world decisions. However, evaluating bias in LLM outputs remains methodologically challenging due to sensitivity to prompt…

Computation and Language · Computer Science 2026-01-13 William Guey , Wei Zhang , Pei-Luen Patrick Rau , Pierrick Bougault , Vitor D. de Moura , Bertan Ucar , Jose O. Gomes

We introduce Harmonic Robustness, a powerful and intuitive method to test the robustness of any machine-learning model either during training or in black-box real-time inference monitoring without ground-truth labels. It is based on…

Machine Learning · Computer Science 2024-04-30 Nicholas S. Kersting , Yi Li , Aman Mohanty , Oyindamola Obisesan , Raphael Okochu

Evaluating the programming robustness of large language models (LLMs) is paramount for ensuring their reliability in AI-based software development. However, adversarial attacks exhibit fundamental limitations that compromise fair robustness…

Software Engineering · Computer Science 2026-02-17 Sen Fang , Weiyuan Ding , Mengshi Zhang , Zihao Chen , Bowen Xu

As LLM-as-a-Judge emerges as a new paradigm for assessing large language models (LLMs), concerns have been raised regarding the alignment, bias, and stability of LLM evaluators. While substantial work has focused on alignment and bias,…

Computation and Language · Computer Science 2025-03-04 Qiujie Xie , Qingqiu Li , Zhuohao Yu , Yuejie Zhang , Yue Zhang , Linyi Yang

The reliable application of deep learning models to software engineering tasks hinges on high-quality training data. Yet, large-scale repositories inevitably introduce noisy or mislabeled examples that degrade both accuracy and robustness.…

Software Engineering · Computer Science 2025-12-05 Zixiao Zhao , Fatemeh H. Fard , Jie JW Wu