English
Related papers

Related papers: Evaluating Performance Drift from Model Switching …

200 papers

As large language models are deployed as autonomous agents with tool execution privileges, a critical assumption underpins their security architecture: that model errors are detectable at runtime. We present empirical evidence that this…

Artificial Intelligence · Computer Science 2026-03-24 Gregory M. Ruddell

Temporal concept drift refers to the problem of data changing over time. In NLP, that would entail that language (e.g. new expressions, meaning shifts) and factual knowledge (e.g. new concepts, updated facts) evolve over time. Focusing on…

Computation and Language · Computer Science 2023-02-27 Katerina Margatina , Shuai Wang , Yogarshi Vyas , Neha Anna John , Yassine Benajiba , Miguel Ballesteros

An exciting advancement in the field of multilingual models is the emergence of autoregressive models with zero- and few-shot capabilities, a phenomenon widely reported in large-scale language models. To further improve model adaptation to…

Computation and Language · Computer Science 2023-11-15 Nohil Park , Joonsuk Park , Kang Min Yoo , Sungroh Yoon

Moral benchmarks for LLMs typically score models on context-free prompts, implicitly treating the measured choice rate as stable. We test this assumption with a direction-flipped influence audit: for each scenario, we compare a baseline…

Machine Learning · Computer Science 2026-05-11 Phil Blandfort , Tushar Karayil , Alex McKenzie , Urja Pawar , Robert Graham , Dmitrii Krasheninnikov

Large language models (LLMs) often require fine-tuning (FT) to perform well on downstream tasks, but FT can induce safety-alignment drift even when the training dataset contains only benign data. Prior work shows that introducing a small…

Computation and Language · Computer Science 2026-03-10 Guoli Wang , Haonan Shi , Tu Ouyang , An Wang

Final outputs hide when a checkpoint commits to its next-token prediction. We introduce the convergence gap, a model-diffing diagnostic that decodes each layer's next-token distribution and measures its distance to the model's own final…

Machine Learning · Computer Science 2026-05-11 Yifan Zhou

LLMs are increasingly used as long-running conversational agents, yet every major benchmark evaluating their memory treats user information as static facts to be stored and retrieved. That's the wrong model. People change their minds, and…

Computation and Language · Computer Science 2026-03-26 Praveen Kumar Myakala , Manan Agrawal , Rahul Manche

Large language models (LLMs) are increasingly deployed in domains where errors carry high social, scientific, or safety costs. Yet standard confidence estimators, such as token likelihood, semantic similarity and multi-sample consistency,…

Computation and Language · Computer Science 2026-02-03 Pengyue Yang , Jiawen Wen , Haolin Jin , Linghan Huang , Huaming Chen , Ling Chen

Hybrid Language Models (HLMs) combine the low-latency efficiency of Small Language Models (SLMs) on edge devices with the high accuracy of Large Language Models (LLMs) on centralized servers. Unlike traditional end-to-end LLM inference,…

Machine Learning · Computer Science 2025-07-02 Faranaksadat Solat , Joohyung Lee , Mohamed Seif , Dusit Niyato , H. Vincent Poor

The interactive nature of Large Language Models (LLMs) theoretically allows models to refine and improve their answers, yet systematic analysis of the multi-turn behavior of LLMs remains limited. In this paper, we propose the FlipFlop…

Computation and Language · Computer Science 2024-02-22 Philippe Laban , Lidiya Murakhovs'ka , Caiming Xiong , Chien-Sheng Wu

Discrete optimization-based jailbreaking attacks on large language models aim to generate short, nonsensical suffixes that, when appended onto input prompts, elicit disallowed content. Notably, these suffixes are often transferable --…

Computation and Language · Computer Science 2025-10-28 Sarah Ball , Niki Hasrati , Alexander Robey , Avi Schwarzschild , Frauke Kreuter , Zico Kolter , Andrej Risteski

Finetuning language models with reinforcement learning (RL), e.g. from human feedback (HF), is a prominent method for alignment. But optimizing against a reward model can improve on reward while degrading performance in other areas, a…

Computation and Language · Computer Science 2023-12-14 Michael Noukhovitch , Samuel Lavoie , Florian Strub , Aaron Courville

Fine-tuning Large Language Models (LLMs) on some task-specific datasets has been a primary use of LLMs. However, it has been empirically observed that this approach to enhancing capability inevitably compromises safety, a phenomenon also…

Machine Learning · Statistics 2025-03-28 Pin-Yu Chen , Han Shen , Payel Das , Tianyi Chen

The dynamicity of real-world systems poses a significant challenge to deployed predictive machine learning (ML) models. Changes in the system on which the ML model has been trained may lead to performance degradation during the system's…

Machine Learning · Computer Science 2022-03-22 Firas Bayram , Bestoun S. Ahmed , Andreas Kassler

Transformer-based pre-trained language models (PLMs) mostly suffer from excessive overhead despite their advanced capacity. For resource-constrained devices, there is an urgent need for a spatially and temporally efficient model which…

Computation and Language · Computer Science 2022-10-28 Bowen Shen , Zheng Lin , Yuanxin Liu , Zhengxiao Liu , Lei Wang , Weiping Wang

Alignment training has tradeoffs: it helps language models (LMs) gain in reasoning and instruction following but might lose out on skills such as creativity and calibration, where unaligned base models are better at. We aim to make the best…

Computation and Language · Computer Science 2025-10-14 Shangbin Feng , Wenhao Yu , Yike Wang , Hongming Zhang , Yulia Tsvetkov , Dong Yu

Progress in LLMs is increasingly measured through standardized benchmarks, where state-of-the-art improvements are often separated by fractions of a percentage point. At the same time, the computational cost of evaluating modern LLMs has…

Machine Learning · Computer Science 2026-05-21 David Pape , Jonathan Evertz , Lea Schönherr

With the proliferation of red-teaming strategies for Large Language Models (LLMs), the deficiency in the literature about improving the safety and robustness of LLM defense strategies is becoming increasingly pronounced. This paper…

Computation and Language · Computer Science 2024-06-19 Jiaxu Liu , Xiangyu Yin , Sihao Wu , Jianhong Wang , Meng Fang , Xinping Yi , Xiaowei Huang

As large language models (LLMs) continue to improve and see further integration into software systems, so does the need to understand the conditions in which they will perform. We contribute a statistical framework for understanding the…

Machine Learning · Computer Science 2026-03-31 Andrew Lauziere , Jonathan Daugherty , Taisa Kushner

Large language models (LLMs) are increasingly being adapted to achieve task-specificity for deployment in real-world decision systems. Several previous works have investigated the bias transfer hypothesis (BTH) by studying the effect of the…

Computation and Language · Computer Science 2024-12-05 Natalie Mackraz , Nivedha Sivakumar , Samira Khorshidi , Krishna Patel , Barry-John Theobald , Luca Zappella , Nicholas Apostoloff