MATH-Perturb: Benchmarking LLMs' Math Reasoning Abilities against Hard Perturbations

Large language models have demonstrated impressive performance on challenging mathematical reasoning tasks, which has triggered the discussion of whether the performance is achieved by true reasoning capability or memorization. To investigate this question, prior work has constructed mathematical benchmarks when questions undergo simple perturbations -- modifications that still preserve the underlying reasoning patterns of the solutions. However, no work has explored hard perturbations, which fundamentally change the nature of the problem so that the original solution steps do not apply. To bridge the gap, we construct MATH-P-Simple and MATH-P-Hard via simple perturbation and hard perturbation, respectively. Each consists of 279 perturbed math problems derived from level-5 (hardest) problems in the MATH dataset (Hendrycksmath et. al., 2021). We observe significant performance drops on MATH-P-Hard across various models, including o1-mini (-16.49%) and gemini-2.0-flash-thinking (-12.9%). We also raise concerns about a novel form of memorization where models blindly apply learned problem-solving skills without assessing their applicability to modified contexts. This issue is amplified when using original problems for in-context learning. We call for research efforts to address this challenge, which is critical for developing more robust and reliable reasoning models.

Scaling Embedding Layers in Language Models

We propose SCONE ($\textbf{S}$calable, $\textbf{C}$ontextualized, $\textbf{O}$ffloaded, $\textbf{N}$-gram $\textbf{E}$mbedding), a method for extending input embedding layers to enhance language model performance as layer size scales. To avoid increased decoding costs, SCONE retains the original vocabulary while introducing embeddings for a set of frequent $n$-grams. These embeddings provide contextualized representation for each input token and are learned with a separate model during training. During inference, they are precomputed and stored in off-accelerator memory with minimal impact on inference speed. SCONE enables two new scaling strategies: increasing the number of cached $n$-gram embeddings and scaling the model used to learn them, all while maintaining fixed inference-time FLOPS. We show that scaling both aspects allows SCONE to outperform a 1.9B parameter baseline across diverse corpora, while using only half the inference-time FLOPS.

Scaling Laws for Differentially Private Language Models

Scaling laws have emerged as important components of large language model (LLM) training as they can predict performance gains through scale, and provide guidance on important hyper-parameter choices that would otherwise be expensive. LLMs also rely on large, high-quality training datasets, like those sourced from (sometimes sensitive) user data. Training models on this sensitive user data requires careful privacy protections like differential privacy (DP). However, the dynamics of DP training are significantly different, and consequently their scaling laws are not yet fully understood. In this work, we establish scaling laws that accurately model the intricacies of DP LLM training, providing a complete picture of the compute-privacy-utility tradeoffs and the optimal training configurations in many settings.

Exploring and Mitigating Adversarial Manipulation of Voting-Based Leaderboards

It is now common to evaluate Large Language Models (LLMs) by having humans manually vote to evaluate model outputs, in contrast to typical benchmarks that evaluate knowledge or skill at some particular task. Chatbot Arena, the most popular benchmark of this type, ranks models by asking users to select the better response between two randomly selected models (without revealing which model was responsible for the generations). These platforms are widely trusted as a fair and accurate measure of LLM capabilities. In this paper, we show that if bot protection and other defenses are not implemented, these voting-based benchmarks are potentially vulnerable to adversarial manipulation. Specifically, we show that an attacker can alter the leaderboard (to promote their favorite model or demote competitors) at the cost of roughly a thousand votes (verified in a simulated, offline version of Chatbot Arena). Our attack consists of two steps: first, we show how an attacker can determine which model was used to generate a given reply with more than $95\%$ accuracy; and then, the attacker can use this information to consistently vote for (or against) a target model. Working with the Chatbot Arena developers, we identify, propose, and implement mitigations to improve the robustness of Chatbot Arena against adversarial manipulation, which, based on our analysis, substantially increases the cost of such attacks. Some of these defenses were present before our collaboration, such as bot protection with Cloudflare, malicious user detection, and rate limiting. Others, including reCAPTCHA and login are being integrated to strengthen the security in Chatbot Arena.

Balls-and-Bins Sampling for DP-SGD

We introduce the Balls-and-Bins sampling for differentially private (DP) optimization methods such as DP-SGD. While it has been common practice to use some form of shuffling in DP-SGD implementations, privacy accounting algorithms have typically assumed that Poisson subsampling is used instead. Recent work by Chua et al. (ICML 2024) however pointed out that shuffling based DP-SGD can have a much larger privacy cost in practical regimes of parameters. We show that the Balls-and-Bins sampling achieves the "best-of-both" samplers, namely, the implementation of Balls-and-Bins sampling is similar to that of Shuffling and models trained using DP-SGD with Balls-and-Bins sampling achieve utility comparable to those trained using DP-SGD with Shuffling at the same noise multiplier, and yet, Balls-and-Bins sampling enjoys similar-or-better privacy amplification as compared to Poisson subsampling in practical regimes.

Scalable DP-SGD: Shuffling vs. Poisson Subsampling

We provide new lower bounds on the privacy guarantee of the multi-epoch Adaptive Batch Linear Queries (ABLQ) mechanism with shuffled batch sampling, demonstrating substantial gaps when compared to Poisson subsampling; prior analysis was limited to a single epoch. Since the privacy analysis of Differentially Private Stochastic Gradient Descent (DP-SGD) is obtained by analyzing the ABLQ mechanism, this brings into serious question the common practice of implementing shuffling-based DP-SGD, but reporting privacy parameters as if Poisson subsampling was used. To understand the impact of this gap on the utility of trained machine learning models, we introduce a practical approach to implement Poisson subsampling at scale using massively parallel computation, and efficiently train models with the same. We compare the utility of models trained with Poisson-subsampling-based DP-SGD, and the optimistic estimates of utility when using shuffling, via our new lower bounds on the privacy guarantee of ABLQ with shuffling.

On Memorization of Large Language Models in Logical Reasoning

Large language models (LLMs) achieve good performance on challenging reasoning benchmarks, yet could also make basic reasoning mistakes. This contrasting behavior is puzzling when it comes to understanding the mechanisms behind LLMs' reasoning capabilities. One hypothesis is that the increasingly high and nearly saturated performance on common reasoning benchmarks could be due to the memorization of similar problems. In this paper, we systematically investigate this hypothesis with a quantitative measurement of memorization in reasoning tasks, using a dynamically generated logical reasoning benchmark based on Knights and Knaves (K&K) puzzles. We found that LLMs could interpolate the training puzzles (achieving near-perfect accuracy) after fine-tuning, yet fail when those puzzles are slightly perturbed, suggesting that the models heavily rely on memorization to solve those training puzzles. On the other hand, we show that while fine-tuning leads to heavy memorization, it also consistently improves generalization performance. In-depth analyses with perturbation tests, cross difficulty-level transferability, probing model internals, and fine-tuning with wrong answers suggest that the LLMs learn to reason on K&K puzzles despite training data memorization. This phenomenon indicates that LLMs exhibit a complex interplay between memorization and genuine reasoning abilities. Finally, our analysis with per-sample memorization score sheds light on how LLMs switch between reasoning and memorization in solving logical puzzles. Our code and data are available at https://memkklogic.github.io.

MUSE: Machine Unlearning Six-Way Evaluation for Language Models

Language models (LMs) are trained on vast amounts of text data, which may include private and copyrighted content. Data owners may request the removal of their data from a trained model due to privacy or copyright concerns. However, exactly unlearning only these datapoints (i.e., retraining with the data removed) is intractable in modern-day models. This has led to the development of many approximate unlearning algorithms. The evaluation of the efficacy of these algorithms has traditionally been narrow in scope, failing to precisely quantify the success and practicality of the algorithm from the perspectives of both the model deployers and the data owners. We address this issue by proposing MUSE, a comprehensive machine unlearning evaluation benchmark that enumerates six diverse desirable properties for unlearned models: (1) no verbatim memorization, (2) no knowledge memorization, (3) no privacy leakage, (4) utility preservation on data not intended for removal, (5) scalability with respect to the size of removal requests, and (6) sustainability over sequential unlearning requests. Using these criteria, we benchmark how effectively eight popular unlearning algorithms on 7B-parameter LMs can unlearn Harry Potter books and news articles. Our results demonstrate that most algorithms can prevent verbatim memorization and knowledge memorization to varying degrees, but only one algorithm does not lead to severe privacy leakage. Furthermore, existing algorithms fail to meet deployer's expectations because they often degrade general model utility and also cannot sustainably accommodate successive unlearning requests or large-scale content removal. Our findings identify key issues with the practicality of existing unlearning algorithms on language models, and we release our benchmark to facilitate further evaluations: muse-bench.github.io

On Convex Optimization with Semi-Sensitive Features

We study the differentially private (DP) empirical risk minimization (ERM) problem under the semi-sensitive DP setting where only some features are sensitive. This generalizes the Label DP setting where only the label is sensitive. We give improved upper and lower bounds on the excess risk for DP-ERM. In particular, we show that the error only scales polylogarithmically in terms of the sensitive domain size, improving upon previous results that scale polynomially in the sensitive domain size (Ghazi et al., 2021).

Evaluating Copyright Takedown Methods for Language Models

Language models (LMs) derive their capabilities from extensive training on diverse data, including potentially copyrighted material. These models can memorize and generate content similar to their training data, posing potential concerns. Therefore, model creators are motivated to develop mitigation methods that prevent generating protected content. We term this procedure as copyright takedowns for LMs, noting the conceptual similarity to (but legal distinction from) the DMCA takedown This paper introduces the first evaluation of the feasibility and side effects of copyright takedowns for LMs. We propose CoTaEval, an evaluation framework to assess the effectiveness of copyright takedown methods, the impact on the model's ability to retain uncopyrightable factual knowledge from the training data whose recitation is embargoed, and how well the model maintains its general utility and efficiency. We examine several strategies, including adding system prompts, decoding-time filtering interventions, and unlearning approaches. Our findings indicate that no tested method excels across all metrics, showing significant room for research in this unique problem setting and indicating potential unresolved challenges for live policy proposals.