Searcharxiv⌕ Search

arXiv subjects

Himabindu Lakkaraju

Publications and source records attributed to Himabindu Lakkaraju.

At least 37 records · Page 2Linked to original sources
arXiv2025

Detecting LLM-Generated Peer Reviews

The integrity of peer review is fundamental to scientific progress, but the rise of large language models (LLMs) has introduced concerns that some reviewers may rely on these tools to generate reviews rather than writing them independently. Although some venues have banned LLM-assisted reviewing, enforcement remains difficult as existing detection tools cannot reliably distinguish between fully generated reviews and those merely polished with AI assistance. In this work, we address the challenge of detecting LLM-generated reviews. We consider the approach of performing indirect prompt injection via the paper's PDF, prompting the LLM to embed a covert watermark in the generated review, and subsequently testing for presence of the watermark in the review. We identify and address several pitfalls in naïve implementations of this approach. Our primary contribution is a rigorous watermarking and detection framework that offers strong statistical guarantees. Specifically, we introduce watermarking schemes and hypothesis tests that control the family-wise error rate across multiple reviews, achieving higher statistical power than standard corrections such as Bonferroni, while making no assumptions about the nature of human-written reviews. We explore multiple indirect prompt injection strategies -- including font-based embedding and obfuscated prompts -- and evaluate their effectiveness under various reviewer defense scenarios. Our experiments find high success rates in watermark embedding across various LLMs. We also empirically find that our approach is resilient to common reviewer defenses, and that the bounds on error rates in our statistical tests hold in practice. In contrast, we find that Bonferroni-style corrections are too conservative to be useful in this setting.

cs.DL↗
arXiv2025

Soft Best-of-n Sampling for Model Alignment

Best-of-$n$ (BoN) sampling is a practical approach for aligning language model outputs with human preferences without expensive fine-tuning. BoN sampling is performed by generating $n$ responses to a prompt and then selecting the sample that maximizes a reward function. BoN yields high reward values in practice at a distortion cost, as measured by the KL-divergence between the sampled and original distribution. This distortion is coarsely controlled by varying the number of samples: larger $n$ yields a higher reward at a higher distortion cost. We introduce Soft Best-of-$n$ sampling, a generalization of BoN that allows for smooth interpolation between the original distribution and reward-maximizing distribution through a temperature parameter $λ$. We establish theoretical guarantees showing that Soft Best-of-$n$ sampling converges sharply to the optimal tilted distribution at a rate of $O(1/n)$ in KL and the expected (relative) reward. For sequences of discrete outputs, we analyze an additive reward model that reveals the fundamental limitations of blockwise sampling.

cs.IT↗
arXiv2025

The Disagreement Problem in Explainable Machine Learning: A Practitioner's Perspective

As various post hoc explanation methods are increasingly being leveraged to explain complex models in high-stakes settings, it becomes critical to develop a deeper understanding of whether and when the explanations output by these methods disagree with each other, and how such disagreements are resolved in practice. However, there is little to no research that provides answers to these critical questions. In this work, we formalize and study the disagreement problem in explainable machine learning. More specifically, we define the notion of disagreement between explanations, analyze how often such disagreements occur in practice, and how practitioners resolve these disagreements. We first conduct interviews with data scientists to understand what constitutes disagreement between explanations generated by different methods for the same model prediction, and introduce a novel quantitative framework to formalize this understanding. We then leverage this framework to carry out a rigorous empirical analysis with four real-world datasets, six state-of-the-art post hoc explanation methods, and six different predictive models, to measure the extent of disagreement between the explanations generated by various popular explanation methods. In addition, we carry out an online user study with data scientists to understand how they resolve the aforementioned disagreements. Our results indicate that (1) state-of-the-art explanation methods often disagree in terms of the explanations they output, and (2) machine learning practitioners often employ ad hoc heuristics when resolving such disagreements. These findings suggest that practitioners may be relying on misleading explanations when making consequential decisions. They also underscore the importance of developing principled frameworks for effectively evaluating and comparing explanations output by various explanation techniques.

cs.LG↗
arXiv2025

Towards Interpretable Soft Prompts

Soft prompts have been popularized as a cheap and easy way to improve task-specific LLM performance beyond few-shot prompts. Despite their origin as an automated prompting method, however, soft prompts and other trainable prompts remain a black-box method with no immediately interpretable connections to prompting. We create a novel theoretical framework for evaluating the interpretability of trainable prompts based on two desiderata: faithfulness and scrutability. We find that existing methods do not naturally satisfy our proposed interpretability criterion. Instead, our framework inspires a new direction of trainable prompting methods that explicitly optimizes for interpretability. To this end, we formulate and test new interpretability-oriented objective functions for two state-of-the-art prompt tuners: Hard Prompts Made Easy (PEZ) and RLPrompt. Our experiments with GPT-2 demonstrate a fundamental trade-off between interpretability and the task-performance of the trainable prompt, explicating the hardness of the soft prompt interpretability problem and revealing odd behavior that arises when one optimizes for an interpretability proxy.

cs.LG↗
arXiv2025

On the Impact of Fine-Tuning on Chain-of-Thought Reasoning

Large language models have emerged as powerful tools for general intelligence, showcasing advanced natural language processing capabilities that find applications across diverse domains. Despite their impressive performance, recent studies have highlighted the potential for significant enhancements in LLMs' task-specific performance through fine-tuning strategies like Reinforcement Learning with Human Feedback (RLHF), supervised fine-tuning (SFT), and Quantized Low-Rank Adapters (Q-LoRA) method. However, previous works have shown that while fine-tuning offers significant performance gains, it also leads to challenges such as catastrophic forgetting and privacy and safety risks. To this end, there has been little to no work in \textit{understanding the impact of fine-tuning on the reasoning capabilities of LLMs}. Our research investigates the effect of fine-tuning on the reasoning abilities of LLMs, addressing critical questions regarding the impact of task-specific fine-tuning on overall reasoning capabilities, the influence of fine-tuning on Chain-of-Thought (CoT) reasoning performance, and the implications for the faithfulness of CoT reasonings. By exploring these dimensions, our study shows the impact of fine-tuning on LLM reasoning capabilities, where the faithfulness of CoT reasoning, on average across four datasets, decreases, highlighting potential shifts in internal mechanisms of the LLMs resulting from fine-tuning processes.

cs.CL↗
arXiv2025

Towards Unifying Interpretability and Control: Evaluation via Intervention

With the growing complexity and capability of large language models, a need to understand model reasoning has emerged, often motivated by an underlying goal of controlling and aligning models. While numerous interpretability and steering methods have been proposed as solutions, they are typically designed either for understanding or for control, seldom addressing both. Additionally, the lack of standardized applications, motivations, and evaluation metrics makes it difficult to assess methods' practical utility and efficacy. To address the aforementioned issues, we argue that intervention is a fundamental goal of interpretability and introduce success criteria to evaluate how well methods can control model behavior through interventions. To evaluate existing methods for this ability, we unify and extend four popular interpretability methods-sparse autoencoders, logit lens, tuned lens, and probing-into an abstract encoder-decoder framework, enabling interventions on interpretable features that can be mapped back to latent representations to control model outputs. We introduce two new evaluation metrics: intervention success rate and coherence-intervention tradeoff, designed to measure the accuracy of explanations and their utility in controlling model behavior. Our findings reveal that (1) while current methods allow for intervention, their effectiveness is inconsistent across features and models, (2) lens-based methods outperform SAEs and probes in achieving simple, concrete interventions, and (3) mechanistic interventions often compromise model coherence, underperforming simpler alternatives, such as prompting, and highlighting a critical shortcoming of current interpretability approaches in applications requiring control.

cs.LG↗
arXiv2025

Certifying LLM Safety against Adversarial Prompting

Large language models (LLMs) are vulnerable to adversarial attacks that add malicious tokens to an input prompt to bypass the safety guardrails of an LLM and cause it to produce harmful content. In this work, we introduce erase-and-check, the first framework for defending against adversarial prompts with certifiable safety guarantees. Given a prompt, our procedure erases tokens individually and inspects the resulting subsequences using a safety filter. Our safety certificate guarantees that harmful prompts are not mislabeled as safe due to an adversarial attack up to a certain size. We implement the safety filter in two ways, using Llama 2 and DistilBERT, and compare the performance of erase-and-check for the two cases. We defend against three attack modes: i) adversarial suffix, where an adversarial sequence is appended at the end of a harmful prompt; ii) adversarial insertion, where the adversarial sequence is inserted anywhere in the middle of the prompt; and iii) adversarial infusion, where adversarial tokens are inserted at arbitrary positions in the prompt, not necessarily as a contiguous block. Our experimental results demonstrate that this procedure can obtain strong certified safety guarantees on harmful prompts while maintaining good empirical performance on safe prompts. Additionally, we propose three efficient empirical defenses: i) RandEC, a randomized subsampling version of erase-and-check; ii) GreedyEC, which greedily erases tokens that maximize the softmax score of the harmful class; and iii) GradEC, which uses gradient information to optimize tokens to erase. We demonstrate their effectiveness against adversarial prompts generated by the Greedy Coordinate Gradient (GCG) attack algorithm. The code for our experiments is available at https://github.com/aounon/certified-llm-safety.

cs.CL↗
arXiv2024

Generalizing Trust: Weak-to-Strong Trustworthiness in Language Models

The rapid proliferation of generative AI, especially large language models, has led to their integration into a variety of applications. A key phenomenon known as weak-to-strong generalization - where a strong model trained on a weak model's outputs surpasses the weak model in task performance - has gained significant attention. Yet, whether critical trustworthiness properties such as robustness, fairness, and privacy can generalize similarly remains an open question. In this work, we study this question by examining if a stronger model can inherit trustworthiness properties when fine-tuned on a weaker model's outputs, a process we term weak-to-strong trustworthiness generalization. To address this, we introduce two foundational training strategies: 1) Weak Trustworthiness Finetuning (Weak TFT), which leverages trustworthiness regularization during the fine-tuning of the weak model, and 2) Weak and Weak-to-Strong Trustworthiness Finetuning (Weak+WTS TFT), which extends regularization to both weak and strong models. Our experimental evaluation on real-world datasets reveals that while some trustworthiness properties, such as fairness, adversarial, and OOD robustness, show significant improvement in transfer when both models were regularized, others like privacy do not exhibit signs of weak-to-strong trustworthiness. As the first study to explore trustworthiness generalization via weak-to-strong generalization, our work provides valuable insights into the potential and limitations of weak-to-strong generalization.

cs.LG↗
arXiv2024

More RLHF, More Trust? On The Impact of Preference Alignment On Trustworthiness

The trustworthiness of Large Language Models (LLMs) refers to the extent to which their outputs are reliable, safe, and ethically aligned, and it has become a crucial consideration alongside their cognitive performance. In practice, Reinforcement Learning From Human Feedback (RLHF) has been widely used to align LLMs with labeled human preferences, but its assumed effect on model trustworthiness hasn't been rigorously evaluated. To bridge this knowledge gap, this study investigates how models aligned with general-purpose preference data perform across five trustworthiness verticals: toxicity, stereotypical bias, machine ethics, truthfulness, and privacy. Our results demonstrate that RLHF on human preferences doesn't automatically guarantee trustworthiness, and reverse effects are often observed. Furthermore, we propose to adapt efficient influence function based data attribution methods to the RLHF setting to better understand the influence of fine-tuning data on individual trustworthiness benchmarks, and show its feasibility by providing our estimated attribution scores. Together, our results underscore the need for more nuanced approaches for model alignment from both the data and framework perspectives, and we hope this research will guide the community towards developing language models that are increasingly capable without sacrificing trustworthiness.

cs.CL↗
arXiv2024

Interpretability Needs a New Paradigm

Interpretability is the study of explaining models in understandable terms to humans. At present, interpretability is divided into two paradigms: the intrinsic paradigm, which believes that only models designed to be explained can be explained, and the post-hoc paradigm, which believes that black-box models can be explained. At the core of this debate is how each paradigm ensures its explanations are faithful, i.e., true to the model's behavior. This is important, as false but convincing explanations lead to unsupported confidence in artificial intelligence (AI), which can be dangerous. This paper's position is that we should think about new paradigms while staying vigilant regarding faithfulness. First, by examining the history of paradigms in science, we see that paradigms are constantly evolving. Then, by examining the current paradigms, we can understand their underlying beliefs, the value they bring, and their limitations. Finally, this paper presents 3 emerging paradigms for interpretability. The first paradigm designs models such that faithfulness can be easily measured. Another optimizes models such that explanations become faithful. The last paradigm proposes to develop models that produce both a prediction and an explanation.

cs.LG↗
arXiv2024

Interpreting CLIP with Sparse Linear Concept Embeddings (SpLiCE)

CLIP embeddings have demonstrated remarkable performance across a wide range of multimodal applications. However, these high-dimensional, dense vector representations are not easily interpretable, limiting our understanding of the rich structure of CLIP and its use in downstream applications that require transparency. In this work, we show that the semantic structure of CLIP's latent space can be leveraged to provide interpretability, allowing for the decomposition of representations into semantic concepts. We formulate this problem as one of sparse recovery and propose a novel method, Sparse Linear Concept Embeddings, for transforming CLIP representations into sparse linear combinations of human-interpretable concepts. Distinct from previous work, SpLiCE is task-agnostic and can be used, without training, to explain and even replace traditional dense CLIP representations, maintaining high downstream performance while significantly improving their interpretability. We also demonstrate significant use cases of SpLiCE representations including detecting spurious correlations and model editing.

cs.LG↗
arXiv2024

Generalized Group Data Attribution

Data Attribution (DA) methods quantify the influence of individual training data points on model outputs and have broad applications such as explainability, data selection, and noisy label identification. However, existing DA methods are often computationally intensive, limiting their applicability to large-scale machine learning models. To address this challenge, we introduce the Generalized Group Data Attribution (GGDA) framework, which computationally simplifies DA by attributing to groups of training points instead of individual ones. GGDA is a general framework that subsumes existing attribution methods and can be applied to new DA techniques as they emerge. It allows users to optimize the trade-off between efficiency and fidelity based on their needs. Our empirical results demonstrate that GGDA applied to popular DA methods such as Influence Functions, TracIn, and TRAK results in upto 10x-50x speedups over standard DA methods while gracefully trading off attribution fidelity. For downstream applications such as dataset pruning and noisy label identification, we demonstrate that GGDA significantly improves computational efficiency and maintains effectiveness, enabling practical applications in large-scale machine learning scenarios that were previously infeasible.

cs.LG↗
arXiv2024

MedSafetyBench: Evaluating and Improving the Medical Safety of Large Language Models

As large language models (LLMs) develop increasingly sophisticated capabilities and find applications in medical settings, it becomes important to assess their medical safety due to their far-reaching implications for personal and public health, patient safety, and human rights. However, there is little to no understanding of the notion of medical safety in the context of LLMs, let alone how to evaluate and improve it. To address this gap, we first define the notion of medical safety in LLMs based on the Principles of Medical Ethics set forth by the American Medical Association. We then leverage this understanding to introduce MedSafetyBench, the first benchmark dataset designed to measure the medical safety of LLMs. We demonstrate the utility of MedSafetyBench by using it to evaluate and improve the medical safety of LLMs. Our results show that publicly-available medical LLMs do not meet standards of medical safety and that fine-tuning them using MedSafetyBench improves their medical safety while preserving their medical performance. By introducing this new benchmark dataset, our work enables a systematic study of the state of medical safety in LLMs and motivates future work in this area, paving the way to mitigate the safety risks of LLMs in medicine. The benchmark dataset and code are available at https://github.com/AI4LIFE-GROUP/med-safety-bench.

cs.AI↗
arXiv2024

Follow My Instruction and Spill the Beans: Scalable Data Extraction from Retrieval-Augmented Generation Systems

Retrieval-Augmented Generation (RAG) improves pre-trained models by incorporating external knowledge at test time to enable customized adaptation. We study the risk of datastore leakage in Retrieval-In-Context RAG Language Models (LMs). We show that an adversary can exploit LMs' instruction-following capabilities to easily extract text data verbatim from the datastore of RAG systems built with instruction-tuned LMs via prompt injection. The vulnerability exists for a wide range of modern LMs that span Llama2, Mistral/Mixtral, Vicuna, SOLAR, WizardLM, Qwen1.5, and Platypus2, and the exploitability exacerbates as the model size scales up. We also study multiple effects of RAG setup on the extractability of data, indicating that following unexpected instructions to regurgitate data can be an outcome of failure in effectively utilizing contexts for modern LMs, and further show that such vulnerability can be greatly mitigated by position bias elimination strategies. Extending our study to production RAG models GPTs, we design an attack that can cause datastore leakage with a 100% success rate on 25 randomly selected customized GPTs with at most 2 queries, and we extract text data verbatim at a rate of 41% from a book of 77,000 words and 3% from a corpus of 1,569,000 words by prompting the GPTs with only 100 queries generated by themselves.

cs.CL↗
arXiv2024

Quantifying Generalization Complexity for Large Language Models

While large language models (LLMs) have shown exceptional capabilities in understanding complex queries and performing sophisticated tasks, their generalization abilities are often deeply entangled with memorization, necessitating more precise evaluation. To address this challenge, we introduce Scylla, a dynamic evaluation framework that quantitatively measures the generalization abilities of LLMs. Scylla disentangles generalization from memorization via assessing model performance on both in-distribution (ID) and out-of-distribution (OOD) data through 20 tasks across 5 levels of complexity. Through extensive experiments, we uncover a non-monotonic relationship between task complexity and the performance gap between ID and OOD data, which we term the generalization valley. Specifically, this phenomenon reveals a critical threshold - referred to as critical complexity - where reliance on non-generalizable behavior peaks, indicating the upper bound of LLMs' generalization capabilities. As model size increases, the critical complexity shifts toward higher levels of task complexity, suggesting that larger models can handle more complex reasoning tasks before over-relying on memorization. Leveraging Scylla and the concept of critical complexity, we benchmark 28LLMs including both open-sourced models such as LLaMA and Qwen families, and close-sourced models like Claude and GPT, providing a more robust evaluation and establishing a clearer understanding of LLMs' generalization capabilities.

cs.CL↗
arXiv2024

Learning Recourse Costs from Pairwise Feature Comparisons

This paper presents a novel technique for incorporating user input when learning and inferring user preferences. When trying to provide users of black-box machine learning models with actionable recourse, we often wish to incorporate their personal preferences about the ease of modifying each individual feature. These recourse finding algorithms usually require an exhaustive set of tuples associating each feature to its cost of modification. Since it is hard to obtain such costs by directly surveying humans, in this paper, we propose the use of the Bradley-Terry model to automatically infer feature-wise costs using non-exhaustive human comparison surveys. We propose that users only provide inputs comparing entire recourses, with all candidate feature modifications, determining which recourses are easier to implement relative to others, without explicit quantification of their costs. We demonstrate the efficient learning of individual feature costs using MAP estimates, and show that these non-exhaustive human surveys, which do not necessarily contain data for each feature pair comparison, are sufficient to learn an exhaustive set of feature costs, where each feature is associated with a modification cost.

cs.LG↗
arXiv2024

Manipulating Large Language Models to Increase Product Visibility

Large language models (LLMs) are increasingly being integrated into search engines to provide natural language responses tailored to user queries. Customers and end-users are also becoming more dependent on these models for quick and easy purchase decisions. In this work, we investigate whether recommendations from LLMs can be manipulated to enhance a product's visibility. We demonstrate that adding a strategic text sequence (STS) -- a carefully crafted message -- to a product's information page can significantly increase its likelihood of being listed as the LLM's top recommendation. To understand the impact of STS, we use a catalog of fictitious coffee machines and analyze its effect on two target products: one that seldom appears in the LLM's recommendations and another that usually ranks second. We observe that the strategic text sequence significantly enhances the visibility of both products by increasing their chances of appearing as the top recommendation. This ability to manipulate LLM-generated search responses provides vendors with a considerable competitive advantage and has the potential to disrupt fair market competition. Just as search engine optimization (SEO) revolutionized how webpages are customized to rank higher in search engine results, influencing LLM recommendations could profoundly impact content optimization for AI-driven search services. Code for our experiments is available at https://github.com/aounon/llm-rank-optimizer.

cs.IR↗
arXiv2024

On the Trade-offs between Adversarial Robustness and Actionable Explanations

As machine learning models are increasingly being employed in various high-stakes settings, it becomes important to ensure that predictions of these models are not only adversarially robust, but also readily explainable to relevant stakeholders. However, it is unclear if these two notions can be simultaneously achieved or if there exist trade-offs between them. In this work, we make one of the first attempts at studying the impact of adversarially robust models on actionable explanations which provide end users with a means for recourse. We theoretically and empirically analyze the cost (ease of implementation) and validity (probability of obtaining a positive model prediction) of recourses output by state-of-the-art algorithms when the underlying models are adversarially robust vs. non-robust. More specifically, we derive theoretical bounds on the differences between the cost and the validity of the recourses generated by state-of-the-art algorithms for adversarially robust vs. non-robust linear and non-linear models. Our empirical results with multiple real-world datasets validate our theoretical results and show the impact of varying degrees of model robustness on the cost and validity of the resulting recourses. Our analyses demonstrate that adversarially robust models significantly increase the cost and reduce the validity of the resulting recourses, thus shedding light on the inherent trade-offs between adversarial robustness and actionable explanations.

cs.LG↗