arXiv subjects

Domenic Rosati

Publications and source records attributed to Domenic Rosati.

At least 19 recordsLinked to original sources

arXiv2026

Distribution-Specific Curvature Control with Finite-Sample Guarantees for Open-Weight Safety

A short fine-tuning run can undo the safety guards of an open-weight model---retraining a refusal-trained assistant to aid weapons development or produce hate speech. Preventing such harmful fine-tuning while retaining benign adaptability remains difficult: the only prior method with an explicit curvature certificate, spectral deformation, inflates curvature globally and thereby obstructs benign adaptation along with harmful adaptation. We propose HarmAlign, which applies function-preserving spectral deformation along a estimated contrastive activation subspace. We derive finite-sample bounds for the estimated subspace energy and the resulting local harmful-distribution curvature lower bound. A stability--progress dichotomy for constant-step gradient descent turns the certified curvature into conditional convergence-rate control. Empirically, within a fixed-architecture, finite-budget first-order threat model, HarmAlign blocks direct fine-tuning and three data- or objective-adaptive attacks across a hazardous-knowledge relearning setting and a harmful-assistance fine-tuning setting, while the protected benign tasks remain trainable. The block persists across the tested first-order optimizer variants over every attack checkpoint, and under out-of-distribution harmful fine-tuning, and it extends to important cases in our threat model: accidental safety degradation and emergent misalignment.

cs.LG↗

arXiv2026

LLMs Underperform Graph-Based Parsers on Supervised Relation Extraction for Complex Graphs

Relation extraction represents a fundamental component in the process of creating knowledge graphs, among other applications. Large language models (LLMs) have been adopted as a promising tool for relation extraction, both in supervised and in-context learning settings. However, in this work we show that their performance still lags behind much smaller architectures when the linguistic graph underlying a text has great complexity. To demonstrate this, we evaluate four LLMs against a graph-based parser on six relation extraction datasets with sentence graphs of varying sizes and complexities. Our results show that the graph-based parser increasingly outperforms the LLMs, as the number of relations in the input documents increases. This makes the much lighter graph-based parser a superior choice in the presence of complex linguistic graphs.

cs.CL↗

arXiv2026

Limits of Convergence-Rate Control for Open-Weight Safety

Open-weight foundation models can be fine-tuned for harmful purposes after release, yet no existing training resistance methods provide theoretical guarantees. Treating these interventions as convergence-rate control problems allows us to connect optimization speed to the spectral structure of model weights. We leverage this insight to develop a novel understanding of convergence rate control through spectral reparameterization and derive an algorithm, SpecDef, that can both provably and empirically slow first- and second-order optimization in non-adversarial settings. In adversarial settings, we establish a fundamental limit on a broad class of convergence rate control methods including our own: an attacker with sufficient knowledge can restore fast convergence at a linear increase in model size. In order to overcome this limitation, future works will need to investigate methods that are not equivalent to controlling convergence rate.

math.OC↗

arXiv2025

Dependency Parsing is More Parameter-Efficient with Normalization

Dependency parsing is the task of inferring natural language structure, often approached by modeling word interactions via attention through biaffine scoring. This mechanism works like self-attention in Transformers, where scores are calculated for every pair of words in a sentence. However, unlike Transformer attention, biaffine scoring does not use normalization prior to taking the softmax of the scores. In this paper, we provide theoretical evidence and empirical results revealing that a lack of normalization necessarily results in overparameterized parser models, where the extra parameters compensate for the sharp softmax outputs produced by high variance inputs to the biaffine scoring function. We argue that biaffine scoring can be made substantially more efficient by performing score normalization. We conduct experiments on semantic and syntactic dependency parsing in multiple languages, along with latent graph inference on non-linguistic data, using various settings of a $k$-hop parser. We train $N$-layer stacked BiLSTMs and evaluate the parser's performance with and without normalizing biaffine scores. Normalizing allows us to achieve state-of-the-art performance with fewer samples and trainable parameters. Code: https://github.com/paolo-gajo/EfficientSDP

cs.CL↗

arXiv2025

Model Tampering Attacks Enable More Rigorous Evaluations of LLM Capabilities

Evaluations of large language model (LLM) risks and capabilities are increasingly being incorporated into AI risk management and governance frameworks. Currently, most risk evaluations are conducted by designing inputs that elicit harmful behaviors from the system. However, this approach suffers from two limitations. First, input-output evaluations cannot fully evaluate realistic risks from open-weight models. Second, the behaviors identified during any particular input-output evaluation can only lower-bound the model's worst-possible-case input-output behavior. As a complementary method for eliciting harmful behaviors, we propose evaluating LLMs with model tampering attacks which allow for modifications to latent activations or weights. We pit state-of-the-art techniques for removing harmful LLM capabilities against a suite of 5 input-space and 6 model tampering attacks. In addition to benchmarking these methods against each other, we show that (1) model resilience to capability elicitation attacks lies on a low-dimensional robustness subspace; (2) the success rate of model tampering attacks can empirically predict and offer conservative estimates for the success of held-out input-space attacks; and (3) state-of-the-art unlearning methods can easily be undone within 16 steps of fine-tuning. Together, these results highlight the difficulty of suppressing harmful LLM capabilities and show that model tampering attacks enable substantially more rigorous evaluations than input-space attacks alone.

cs.CR↗

arXiv2025

Consistency in Language Models: Current Landscape, Challenges, and Future Directions

The hallmark of effective language use lies in consistency: expressing similar meanings in similar contexts and avoiding contradictions. While human communication naturally demonstrates this principle, state-of-the-art language models (LMs) struggle to maintain reliable consistency across task- and domain-specific applications. Here we examine the landscape of consistency research in LMs, analyze current approaches to measure aspects of consistency, and identify critical research gaps. Our findings point to an urgent need for quality benchmarks to measure and interdisciplinary approaches to ensure consistency while preserving utility.

cs.CL↗

arXiv2025

Resolving Lexical Bias in Model Editing

Model editing aims to modify the outputs of large language models after they are trained. Previous approaches have often involved direct alterations to model weights, which can result in model degradation. Recent techniques avoid making modifications to the model's weights by using an adapter that applies edits to the model when triggered by semantic similarity in the representation space. We demonstrate that current adapter methods are critically vulnerable to strong lexical biases, leading to issues such as applying edits to irrelevant prompts with overlapping words. This paper presents a principled approach to learning a disentangled representation space that facilitates precise localization of edits by maintaining distance between irrelevant prompts while preserving proximity among paraphrases. In our empirical study, we show that our method (Projector Editor Networks for Model Editing - PENME) achieves state-of-the-art model editing results while being more computationally efficient during inference than previous methods and adaptable across different architectures.

cs.CL↗

arXiv2025

Semantic Consistency for Assuring Reliability of Large Language Models

Large Language Models (LLMs) exhibit remarkable fluency and competence across various natural language tasks. However, recent research has highlighted their sensitivity to variations in input prompts. To deploy LLMs in a safe and reliable manner, it is crucial for their outputs to be consistent when prompted with expressions that carry the same meaning or intent. While some existing work has explored how state-of-the-art LLMs address this issue, their evaluations have been confined to assessing lexical equality of single- or multi-word answers, overlooking the consistency of generative text sequences. For a more comprehensive understanding of the consistency of LLMs in open-ended text generation scenarios, we introduce a general measure of semantic consistency, and formulate multiple versions of this metric to evaluate the performance of various LLMs. Our proposal demonstrates significantly higher consistency and stronger correlation with human evaluations of output consistency than traditional metrics based on lexical consistency. Finally, we propose a novel prompting strategy, called Ask-to-Choose (A2C), to enhance semantic consistency. When evaluated for closed-book question answering based on answer variations from the TruthfulQA benchmark, A2C increases accuracy metrics for pretrained and finetuned LLMs by up to 47%, and semantic consistency metrics for instruction-tuned models by up to 7-fold.

cs.CL↗

arXiv2025

Content-aware rankings: a new approach to rankings in scholarship

Entity rankings (e.g., institutions, journals) are a core component of academia and related industries. Existing approaches to institutional rankings have relied on a variety of data sources, and approaches to computing outcomes, but remain controversial. One limitation of existing approaches is reliance on scholarly output (e.g., number of publications associated with a given institution during a time period). We propose a new approach to rankings - one that relies not on scholarly output, but rather on the type of citations received (an implementation of the Scite Index). We describe how the necessary data can be gathered, as well as how relevant metrics are computed. To demonstrate the utility of our approach, we present rankings of fields, journals, and institutions, and discuss the various ways Scite's data can be deployed in the context of rankings. Implications, limitations, and future directions are discussed.

cs.DL↗

arXiv2025

Evaluating Defences against Unsafe Feedback in RLHF

While there has been progress towards aligning Large Language Models (LLMs) with human values and ensuring safe behaviour at inference time, safety guards can easily be removed when fine tuned on unsafe and harmful datasets. While this setting has been treated extensively, another popular training paradigm, learning from unsafe feedback with reinforcement learning, has previously been unexplored. This is concerning due to the widespread deployment of feedback collection systems. We address this gap by providing an analysis of learning settings where feedback is harmful, i.e. that unsafe samples are preferred over safe ones despite model developers goal to maintain safety. We find that safety-aligned LLMs easily explore unsafe action spaces via generating harmful text and optimize for reward that violates safety constraints indicating that current safety guards are not enough to prevent learning from unsafe feedback. In order to protect against this vulnerability, we adapt a number of both "implict" and "explicit" harmful fine-tuning defences to evaluate whether they are effective as learning constraints in an RLHF setting finding that no method is generally effective pointing to the need for more defence research. We end the paper with the observation that some defences work by performing "harmless reward hacking" for which we provide a theoretical explanation drawn from the theory of Constrained Markov Decision Processes and provide some direction for future defence development.

cs.LG↗

arXiv2025

Improving Consistency in Large Language Models through Chain of Guidance

Consistency is a fundamental dimension of trustworthiness in Large Language Models (LLMs). For humans to be able to trust LLM-based applications, their outputs should be consistent when prompted with inputs that carry the same meaning or intent. Despite this need, there is no known mechanism to control and guide LLMs to be more consistent at inference time. In this paper, we introduce a novel alignment strategy to maximize semantic consistency in LLM outputs. Our proposal is based on Chain of Guidance (CoG), a multistep prompting technique that generates highly consistent outputs from LLMs. For closed-book question-answering (Q&A) tasks, when compared to direct prompting, the outputs generated using CoG show improved consistency. While other approaches like template-based responses and majority voting may offer alternative paths to consistency, our work focuses on exploring the potential of guided prompting. We use synthetic data sets comprised of consistent input-output pairs to fine-tune LLMs to produce consistent and correct outputs. Our fine-tuned models are more than twice as consistent compared to base models and show strong generalization capabilities by producing consistent outputs over datasets not used in the fine-tuning process.

cs.CL↗

arXiv2024

Representation Noising: A Defence Mechanism Against Harmful Finetuning

Releasing open-source large language models (LLMs) presents a dual-use risk since bad actors can easily fine-tune these models for harmful purposes. Even without the open release of weights, weight stealing and fine-tuning APIs make closed models vulnerable to harmful fine-tuning attacks (HFAs). While safety measures like preventing jailbreaks and improving safety guardrails are important, such measures can easily be reversed through fine-tuning. In this work, we propose Representation Noising (RepNoise), a defence mechanism that operates even when attackers have access to the weights. RepNoise works by removing information about harmful representations such that it is difficult to recover them during fine-tuning. Importantly, our defence is also able to generalize across different subsets of harm that have not been seen during the defence process as long as they are drawn from the same distribution of the attack set. Our method does not degrade the general capability of LLMs and retains the ability to train the model on harmless tasks. We provide empirical evidence that the efficacy of our defence lies in its ``depth'': the degree to which information about harmful representations is removed across all layers of the LLM. We also find areas where RepNoise still remains ineffective and highlight how those limitations can inform future research.

cs.CL↗

arXiv2024

Immunization against harmful fine-tuning attacks

Large Language Models (LLMs) are often trained with safety guards intended to prevent harmful text generation. However, such safety training can be removed by fine-tuning the LLM on harmful datasets. While this emerging threat (harmful fine-tuning attacks) has been characterized by previous work, there is little understanding of how we should proceed in constructing and validating defenses against these attacks especially in the case where defenders would not have control of the fine-tuning process. We introduce a formal framework based on the training budget of an attacker which we call "Immunization" conditions. Using a formal characterisation of the harmful fine-tuning problem, we provide a thorough description of what a successful defense must comprise of and establish a set of guidelines on how rigorous defense research that gives us confidence should proceed.

cs.CL↗

arXiv2024

Long-form evaluation of model editing

Evaluations of model editing currently only use the `next few token' completions after a prompt. As a result, the impact of these methods on longer natural language generation is largely unknown. We introduce long-form evaluation of model editing (LEME) a novel evaluation protocol that measures the efficacy and impact of model editing in long-form generative settings. Our protocol consists of a machine-rated survey and a classifier which correlates well with human ratings. Importantly, we find that our protocol has very little relationship with previous short-form metrics (despite being designed to extend efficacy, generalization, locality, and portability into a long-form setting), indicating that our method introduces a novel set of dimensions for understanding model editing methods. Using this protocol, we benchmark a number of model editing techniques and present several findings including that, while some methods (ROME and MEMIT) perform well in making consistent edits within a limited scope, they suffer much more from factual drift than other methods. Finally, we present a qualitative analysis that illustrates common failure modes in long-form generative settings including internal consistency, lexical cohesion, and locality issues.

cs.CL↗

arXiv2023

Self-Consistency of Large Language Models under Ambiguity

Large language models (LLMs) that do not give consistent answers across contexts are problematic when used for tasks with expectations of consistency, e.g., question-answering, explanations, etc. Our work presents an evaluation benchmark for self-consistency in cases of under-specification where two or more answers can be correct. We conduct a series of behavioral experiments on the OpenAI model suite using an ambiguous integer sequence completion task. We find that average consistency ranges from 67\% to 82\%, far higher than would be predicted if a model's consistency was random, and increases as model capability improves. Furthermore, we show that models tend to maintain self-consistency across a series of robustness checks, including prompting speaker changes and sequence length changes. These results suggest that self-consistency arises as an emergent capability without specifically training for it. Despite this, we find that models are uncalibrated when judging their own consistency, with models displaying both over- and under-confidence. We also propose a nonparametric test for determining from token output distribution whether a model assigns non-trivial probability to alternative answers. Using this test, we find that despite increases in self-consistency, models usually place significant weight on alternative, inconsistent answers. This distribution of probability mass provides evidence that even highly self-consistent models internally compute multiple possible responses.

cs.CL↗

arXiv2023

Mixture of Soft Prompts for Controllable Data Generation

Large language models (LLMs) effectively generate fluent text when the target output follows natural language patterns. However, structured prediction tasks confine the output format to a limited ontology, causing even very large models to struggle since they were never trained with such restrictions in mind. The difficulty of using LLMs for direct prediction is exacerbated in few-shot learning scenarios, which commonly arise due to domain shift and resource limitations. We flip the problem on its head by leveraging the LLM as a tool for data augmentation rather than direct prediction. Our proposed Mixture of Soft Prompts (MSP) serves as a parameter-efficient procedure for generating data in a controlled manner. Denoising mechanisms are further applied to improve the quality of synthesized data. Automatic metrics show our method is capable of producing diverse and natural text, while preserving label semantics. Moreover, MSP achieves state-of-the-art results on three benchmarks when compared against strong baselines. Our method offers an alternate data-centric approach for applying LLMs to complex prediction tasks.

cs.CL↗

arXiv2023

Using contradictions improves question answering systems

This work examines the use of contradiction in natural language inference (NLI) for question answering (QA). Typically, NLI systems help answer questions by determining if a potential answer is \emph{entailed} (supported) by some background context. But is it useful to also determine if an answer contradicts the context? We test this in two settings, multiple choice and extractive QA, and find that systems that incorporate contradiction can do slightly better than entailment-only systems on certain datasets. However, the best performances come from using contradiction, entailment, and QA model confidence scores together. This has implications for the deployment of QA systems in domains such as medicine and science where safety is an issue.

cs.CL↗

arXiv2023

Background Knowledge Grounding for Readable, Relevant, and Factual Biomedical Lay Summaries

Communication of scientific findings to the public is important for keeping non-experts informed of developments such as life-saving medical treatments. However, generating readable lay summaries from scientific documents is challenging, and currently, these summaries suffer from critical factual errors. One popular intervention for improving factuality is using additional external knowledge to provide factual grounding. However, it is unclear how these grounding sources should be retrieved, selected, or integrated, and how supplementary grounding documents might affect the readability or relevance of the generated summaries. We develop a simple method for selecting grounding sources and integrating them with source documents. We then use the BioLaySum summarization dataset to evaluate the effects of different grounding sources on summary quality. We found that grounding source documents improves the relevance and readability of lay summaries but does not improve factuality of lay summaries. This continues to be true in zero-shot summarization settings where we hypothesized that grounding might be even more important for factual lay summaries.

cs.CL↗