PROGRESS: Coverage-guided RL to Train Search-augmented LLM Agent

Existing search-augmented LLM agents are trained using Reinforcement Learning to boost its reasoning capabilities. However, these approaches primarily rely on outcome-level rewards, which provide little supervision over search behavior and overlook agent's ability to decompose complex queries properly. To mitigate this issue, we propose PROGRESS which utilizes teacher-guided coverage reward to explicitly shape decomposed query generation of the policy model. During training, frozen teacher models are used to decompose complex queries into essential search queries. These essential search queries are utilized to guide the search behavior of the policy model. Integrated into an R1-style training framework, our approach provides lightweight guidance over query decomposition decisions without dense process-level supervision. Experiments show that coverage-guided RL improves overall task performance, highlighting the importance of explicitly supervising search strategies in agentic LLMs.

Search-GRT: Guided Retrieval Training of Search Agents to Optimize for Complex Question Answering

The effective use of search engines by large language models (LLMs) remains a significant challenge, particularly in complex, multi-hop question-answering (MHQA) tasks. These tasks require the model to decompose questions into subqueries, retrieve relevant information, and synthesize answers from multiple sources, often leading to cascading errors due to poor retrieval in early stages. Reinforcement learning (RL) has shown promise in improving LLMs' search capabilities, but it often suffers from sparse rewards during training, hindering the model's ability to learn effectively. To address these challenges, we introduce Guided Retrieval Training (GRT), a novel method that improves the performance of a search agent by restricting the retrieval process during RL training using ground truth information. By focusing on a curated set of relevant documents, GRT provides the model with a stronger learning signal, mitigating the problem of sparse rewards and improving its ability to generate accurate subqueries and synthesize correct answers. Our experimental results demonstrate that GRT achieves consistent performance improvements over existing methods, such as Search-R1, across a wide range of question-answering (QA) tasks. Notably, GRT excels in MHQA tasks, achieving over 40% improvements in performance. Additionally, GRT enhances training efficiency by achieving better QA performance with fewer training steps.

Detecting LLM-Written Peer Reviews

Editors of academic journals and program chairs of conferences require peer reviewers to write their own reviews. However, there is growing concern about the rise of lazy reviewing practices, where reviewers use large language models (LLMs) to generate reviews instead of writing them independently. Existing tools for detecting LLM-generated content are not designed to differentiate between fully LLM-generated reviews and those merely polished by an LLM. In this work, we employ a straightforward approach to identify LLM-generated reviews - doing an indirect prompt injection via the paper PDF to ask the LLM to embed a watermark. Our focus is on presenting watermarking schemes and statistical tests that maintain a bounded family-wise error rate, when a venue evaluates multiple reviews, with a higher power as compared to standard methods like Bonferroni correction. These guarantees hold without relying on any assumptions about human-written reviews. We also consider various methods for prompt injection including font embedding and jailbreaking. We evaluate the effectiveness and various tradeoffs of these methods, including different reviewer defenses. We find a high success rate in the embedding of our watermarks in LLM-generated reviews across models. We also find that our approach is resilient to common reviewer defenses, and that the bounds on error rates in our statistical tests hold in practice while having the power to flag LLM-generated reviews, while Bonferroni correction is infeasible.

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.

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.

Towards Safe and Aligned Large Language Models for Medicine

The capabilities of large language models (LLMs) have been progressing at a breathtaking speed, leaving even their own developers grappling with the depth of their potential and risks. While initial steps have been taken to evaluate the safety and alignment of general-knowledge LLMs, exposing some weaknesses, to our knowledge, the safety and alignment of medical LLMs has not been evaluated despite their risks for personal health and safety, public health and safety, and human rights. To this end, we carry out the first safety evaluation for medical LLMs. Specifically, we set forth a definition of medical safety and alignment for medical artificial intelligence systems, develop a dataset of harmful medical questions to evaluate the medical safety and alignment of an LLM, evaluate both general and medical safety and alignment of medical LLMs, demonstrate fine-tuning as an effective mitigation strategy, and discuss broader, large-scale approaches used by the machine learning community to develop safe and aligned LLMs. We hope that this work casts light on the safety and alignment of medical LLMs and motivates future work to study it and develop additional mitigation strategies, minimizing the risks of harm of LLMs in medicine.

Robustness of AI-Image Detectors: Fundamental Limits and Practical Attacks

In light of recent advancements in generative AI models, it has become essential to distinguish genuine content from AI-generated one to prevent the malicious usage of fake materials as authentic ones and vice versa. Various techniques have been introduced for identifying AI-generated images, with watermarking emerging as a promising approach. In this paper, we analyze the robustness of various AI-image detectors including watermarking and classifier-based deepfake detectors. For watermarking methods that introduce subtle image perturbations (i.e., low perturbation budget methods), we reveal a fundamental trade-off between the evasion error rate (i.e., the fraction of watermarked images detected as non-watermarked ones) and the spoofing error rate (i.e., the fraction of non-watermarked images detected as watermarked ones) upon an application of a diffusion purification attack. In this regime, we also empirically show that diffusion purification effectively removes watermarks with minimal changes to images. For high perturbation watermarking methods where notable changes are applied to images, the diffusion purification attack is not effective. In this case, we develop a model substitution adversarial attack that can successfully remove watermarks. Moreover, we show that watermarking methods are vulnerable to spoofing attacks where the attacker aims to have real images (potentially obscene) identified as watermarked ones, damaging the reputation of the developers. In particular, by just having black-box access to the watermarking method, we show that one can generate a watermarked noise image which can be added to the real images to have them falsely flagged as watermarked ones. Finally, we extend our theory to characterize a fundamental trade-off between the robustness and reliability of classifier-based deep fake detectors and demonstrate it through experiments.

Certifying LLM Safety against Adversarial Prompting

Large language models (LLMs) released for public use incorporate guardrails to ensure their output is safe, often referred to as "model alignment." An aligned language model should decline a user's request to produce harmful content. However, such safety measures are vulnerable to adversarial prompts, which contain maliciously designed token sequences to circumvent the model's safety guards and cause it to produce harmful content. In this work, we introduce erase-and-check, the first framework to defend against adversarial prompts with verifiable safety guarantees. We erase tokens individually and inspect the resulting subsequences using a safety filter. Our procedure labels the input prompt as harmful if any subsequences or the input prompt are detected as harmful by the filter. This guarantees that any adversarial modification of a harmful prompt up to a certain size is also labeled harmful. We defend against three attack modes: i) adversarial suffix, which appends an adversarial sequence at the end of the 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. Empirical results demonstrate that our technique obtains strong certified safety guarantees on harmful prompts while maintaining good performance on safe prompts. For example, against adversarial suffixes of length 20, it certifiably detects 93% of the harmful prompts and labels 94% of the safe prompts as safe using the open source language model Llama 2 as the safety filter.

Provable Robustness for Streaming Models with a Sliding Window

The literature on provable robustness in machine learning has primarily focused on static prediction problems, such as image classification, in which input samples are assumed to be independent and model performance is measured as an expectation over the input distribution. Robustness certificates are derived for individual input instances with the assumption that the model is evaluated on each instance separately. However, in many deep learning applications such as online content recommendation and stock market analysis, models use historical data to make predictions. Robustness certificates based on the assumption of independent input samples are not directly applicable in such scenarios. In this work, we focus on the provable robustness of machine learning models in the context of data streams, where inputs are presented as a sequence of potentially correlated items. We derive robustness certificates for models that use a fixed-size sliding window over the input stream. Our guarantees hold for the average model performance across the entire stream and are independent of stream size, making them suitable for large data streams. We perform experiments on speech detection and human activity recognition tasks and show that our certificates can produce meaningful performance guarantees against adversarial perturbations.

Can AI-Generated Text be Reliably Detected?

The rapid progress of Large Language Models (LLMs) has made them capable of performing astonishingly well on various tasks including document completion and question answering. The unregulated use of these models, however, can potentially lead to malicious consequences such as plagiarism, generating fake news, spamming, etc. Therefore, reliable detection of AI-generated text can be critical to ensure the responsible use of LLMs. Recent works attempt to tackle this problem either using certain model signatures present in the generated text outputs or by applying watermarking techniques that imprint specific patterns onto them. In this paper, both empirically and theoretically, we show that these detectors are not reliable in practical scenarios. Empirically, we show that paraphrasing attacks, where a light paraphraser is applied on top of the generative text model, can break a whole range of detectors, including the ones using the watermarking schemes as well as neural network-based detectors and zero-shot classifiers. We then provide a theoretical impossibility result indicating that for a sufficiently good language model, even the best-possible detector can only perform marginally better than a random classifier. Finally, we show that even LLMs protected by watermarking schemes can be vulnerable against spoofing attacks where adversarial humans can infer hidden watermarking signatures and add them to their generated text to be detected as text generated by the LLMs, potentially causing reputational damages to their developers. We believe these results can open an honest conversation in the community regarding the ethical and reliable use of AI-generated text.