arXiv subjects

Constanza Fierro

Publications and source records attributed to Constanza Fierro.

15 recordsLinked to original sources

arXiv2026

Latent-Space Intervention for Cross-Lingual Factual Consistency: Consistency Improvements without Accuracy Drops

Large Language Models (LLMs) often answer the same factual question differently across languages. We study whether cross-lingual latent-space intervention can reduce this inconsistency. We train layer-specific autoencoders on parallel multilingual representations and apply inference-time corrections to factual QA prompts. We find that latent intervention improves geometric alignment between languages, and that this improvement translates into consistent gains in cross-lingual consistency with English across both open-ended and multiple-choice QA formats, without degrading factual accuracy. In open-ended QA, Spearman's rank correlation between English and non-English languages improves substantially, with gains of 0.16 for English-Arabic and 0.20 for English-Russian pairs. In multiple-choice QA, answer agreement with English improves consistently across both KLAR and mParaRel. Ablations show that AE reconstruction yields consistent gains at no accuracy cost, while PCA projection contributes marginally, and mean-shift produces substantially larger consistency gains in open-ended QA at the cost of some accuracy.

cs.CL↗

arXiv2026

Pathways of Visual Information Flow in Vision-Language Models

We study how visual information is routed in vision-language models (VLMs). Using causal patching on controlled synthetic and natural datasets, we find that models rely on two distinct pathways to solve visual tasks: A direct pathway, where visual information is retained in image token representations and read out by the final token at later layers, and a text-mediated pathway, where visual information is first transferred to the query tokens and then read out by the final token. Across three visual tasks, we show that pathway selection is task-dependent, and that data distribution and prompt design can also modulate which pathway is used to solve the image-based query. Moreover, using attention knockouts and corrupted-input patching, we find that these pathways are flexible, under certain interventions, models can rely on the text-mediated pathway as a fallback when the usual pathway is ablated. This behavior unifies findings in prior work and shows that ablation-based interventions can reveal what models could do rather than what they normally do. Together, our results provide a mechanistic characterization of visual information flow in VLMs and highlight the flexibility of their internal mechanisms under intervention.

cs.CV↗

arXiv2025

Steering Language Models with Weight Arithmetic

Providing high-quality feedback to Large Language Models (LLMs) on a diverse training distribution can be difficult and expensive, and providing feedback only on a narrow distribution can result in unintended generalizations. To better leverage narrow training data, we propose contrastive weight steering, a simple post-training method that edits the model parameters using weight arithmetic. We isolate a behavior direction in weight-space by subtracting the weight deltas from two small fine-tunes -- one that induces the desired behavior and another that induces its opposite -- and then add or remove this direction to modify the model's weights. We apply this technique to mitigate sycophancy and induce misalignment, and find that weight steering often generalizes further than activation steering, achieving stronger out-of-distribution behavioral control before degrading general capabilities. We also show that, in the context of task-specific fine-tuning, weight steering can partially mitigate undesired behavioral drift: it can reduce sycophancy and under-refusals introduced during fine-tuning while preserving task performance gains. Finally, we provide preliminary evidence that emergent misalignment can be detected by measuring the similarity between fine-tuning updates and an "evil" weight direction, suggesting that it may be possible to monitor the evolution of weights during training and detect rare misaligned behaviors that never manifest during training or evaluations.

cs.CL↗

arXiv2025

Real-Time Progress Prediction in Reasoning Language Models

Recent reasoning language models, particularly those that employ long latent chains of thought, achieve strong performance on complex agentic tasks. However, as these models operate over increasingly long time horizons, their internal progress becomes opaque to users, making expectation management and real-time oversight difficult. In this work, we investigate whether real-time progress prediction is feasible for such models. We first test whether hidden states encode progress information by discretizing reasoning trajectories and training a linear probe to classify reasoning states. We then fine-tune models to generate progress estimates from 0--100\% during chain-of-thought reasoning. Our strongest progress-reporting checkpoint reaches 0.161 MAE on mathematical reasoning traces and outperforms position baselines in this setting. Finally, we quantify the intrinsic ambiguity of progress labels by measuring how much the implied progress value varies from the same partial rollout. This ambiguity is lowest for Qwen3-4B, whose continuations produce the smallest rollout dispersion, suggesting that larger models can make progress labels more stable by reducing variation in remaining solution length.

cs.LG↗

arXiv2025

Mechanistic Interpretability Needs Philosophy

Mechanistic interpretability (MI) aims to explain how neural networks work by uncovering their underlying mechanisms. As the field grows in influence, it is increasingly important to examine not just models themselves, but the assumptions, concepts and explanatory strategies implicit in MI research. We argue that mechanistic interpretability needs philosophy as an ongoing partner in clarifying its concepts, refining its methods, and navigating the epistemic and ethical complexities of interpreting AI systems. There is significant unrealised potential for progress in MI to be gained through deeper engagement with philosophers and philosophical frameworks. Taking three open problems from the MI literature as examples, this paper illustrates the value philosophy can add to MI research, and outlines a path toward deeper interdisciplinary dialogue.

cs.CL↗

arXiv2024

How Do Multilingual Language Models Remember Facts?

Large Language Models (LLMs) store and retrieve vast amounts of factual knowledge acquired during pre-training. Prior research has localized and identified mechanisms behind knowledge recall; however, it has only focused on English monolingual models. The question of how these mechanisms generalize to non-English languages and multilingual LLMs remains unexplored. In this paper, we address this gap by conducting a comprehensive analysis of three multilingual LLMs. First, we show that previously identified recall mechanisms in English largely apply to multilingual contexts, with nuances based on language and architecture. Next, through patching intermediate representations, we localize the role of language during recall, finding that subject enrichment is language-independent, while object extraction is language-dependent. Additionally, we discover that the last token representation acts as a Function Vector (FV), encoding both the language of the query and the content to be extracted from the subject. Furthermore, in decoder-only LLMs, FVs compose these two pieces of information in two separate stages. These insights reveal unique mechanisms in multilingual LLMs for recalling information, highlighting the need for new methodologies -- such as knowledge evaluation, fact editing, and knowledge acquisition -- that are specifically tailored for multilingual LLMs.

cs.CL↗

arXiv2024

Defining Knowledge: Bridging Epistemology and Large Language Models

Knowledge claims are abundant in the literature on large language models (LLMs); but can we say that GPT-4 truly "knows" the Earth is round? To address this question, we review standard definitions of knowledge in epistemology and we formalize interpretations applicable to LLMs. In doing so, we identify inconsistencies and gaps in how current NLP research conceptualizes knowledge with respect to epistemological frameworks. Additionally, we conduct a survey of 100 professional philosophers and computer scientists to compare their preferences in knowledge definitions and their views on whether LLMs can really be said to know. Finally, we suggest evaluation protocols for testing knowledge in accordance to the most relevant definitions.

cs.CL↗

arXiv2024

Does Instruction Tuning Make LLMs More Consistent?

The purpose of instruction tuning is enabling zero-shot performance, but instruction tuning has also been shown to improve chain-of-thought reasoning and value alignment (Si et al., 2023). Here we consider the impact on $\textit{consistency}$, i.e., the sensitivity of language models to small perturbations in the input. We compare 10 instruction-tuned LLaMA models to the original LLaMA-7b model and show that almost across-the-board they become more consistent, both in terms of their representations and their predictions in zero-shot and downstream tasks. We explain these improvements through mechanistic analyses of factual recall.

cs.CL↗

arXiv2024

Learning to Plan and Generate Text with Citations

The increasing demand for the deployment of LLMs in information-seeking scenarios has spurred efforts in creating verifiable systems, which generate responses to queries along with supporting evidence. In this paper, we explore the attribution capabilities of plan-based models which have been recently shown to improve the faithfulness, grounding, and controllability of generated text. We conceptualize plans as a sequence of questions which serve as blueprints of the generated content and its organization. We propose two attribution models that utilize different variants of blueprints, an abstractive model where questions are generated from scratch, and an extractive model where questions are copied from the input. Experiments on long-form question-answering show that planning consistently improves attribution quality. Moreover, the citations generated by blueprint models are more accurate compared to those obtained from LLM-based pipelines lacking a planning component.

cs.CL↗

arXiv2024

MuLan: A Study of Fact Mutability in Language Models

Facts are subject to contingencies and can be true or false in different circumstances. One such contingency is time, wherein some facts mutate over a given period, e.g., the president of a country or the winner of a championship. Trustworthy language models ideally identify mutable facts as such and process them accordingly. We create MuLan, a benchmark for evaluating the ability of English language models to anticipate time-contingency, covering both 1:1 and 1:N relations. We hypothesize that mutable facts are encoded differently than immutable ones, hence being easier to update. In a detailed evaluation of six popular large language models, we consistently find differences in the LLMs' confidence, representations, and update behavior, depending on the mutability of a fact. Our findings should inform future work on the injection of and induction of time-contingent knowledge to/from LLMs.

cs.CL↗

arXiv2023

$\mu$PLAN: Summarizing using a Content Plan as Cross-Lingual Bridge

Cross-lingual summarization consists of generating a summary in one language given an input document in a different language, allowing for the dissemination of relevant content across speakers of other languages. The task is challenging mainly due to the paucity of cross-lingual datasets and the compounded difficulty of summarizing and translating. This work presents $\mu$PLAN, an approach to cross-lingual summarization that uses an intermediate planning step as a cross-lingual bridge. We formulate the plan as a sequence of entities capturing the summary's content and the order in which it should be communicated. Importantly, our plans abstract from surface form: using a multilingual knowledge base, we align entities to their canonical designation across languages and generate the summary conditioned on this cross-lingual bridge and the input. Automatic and human evaluation on the XWikis dataset (across four language pairs) demonstrates that our planning objective achieves state-of-the-art performance in terms of informativeness and faithfulness. Moreover, $\mu$PLAN models improve the zero-shot transfer to new cross-lingual language pairs compared to baselines without a planning component.

cs.CL↗

arXiv2023

Do Vision and Language Models Share Concepts? A Vector Space Alignment Study

Large-scale pretrained language models (LMs) are said to ``lack the ability to connect utterances to the world'' (Bender and Koller, 2020), because they do not have ``mental models of the world' '(Mitchell and Krakauer, 2023). If so, one would expect LM representations to be unrelated to representations induced by vision models. We present an empirical evaluation across four families of LMs (BERT, GPT-2, OPT and LLaMA-2) and three vision model architectures (ResNet, SegFormer, and MAE). Our experiments show that LMs partially converge towards representations isomorphic to those of vision models, subject to dispersion, polysemy and frequency. This has important implications for both multi-modal processing and the LM understanding debate (Mitchell and Krakauer, 2023).

cs.CL↗

arXiv2022

Factual Consistency of Multilingual Pretrained Language Models

Pretrained language models can be queried for factual knowledge, with potential applications in knowledge base acquisition and tasks that require inference. However, for that, we need to know how reliable this knowledge is, and recent work has shown that monolingual English language models lack consistency when predicting factual knowledge, that is, they fill-in-the-blank differently for paraphrases describing the same fact. In this paper, we extend the analysis of consistency to a multilingual setting. We introduce a resource, mParaRel, and investigate (i) whether multilingual language models such as mBERT and XLM-R are more consistent than their monolingual counterparts; and (ii) if such models are equally consistent across languages. We find that mBERT is as inconsistent as English BERT in English paraphrases, but that both mBERT and XLM-R exhibit a high degree of inconsistency in English and even more so for all the other 45 languages.

cs.CL↗

arXiv2022

Challenges and Strategies in Cross-Cultural NLP

Various efforts in the Natural Language Processing (NLP) community have been made to accommodate linguistic diversity and serve speakers of many different languages. However, it is important to acknowledge that speakers and the content they produce and require, vary not just by language, but also by culture. Although language and culture are tightly linked, there are important differences. Analogous to cross-lingual and multilingual NLP, cross-cultural and multicultural NLP considers these differences in order to better serve users of NLP systems. We propose a principled framework to frame these efforts, and survey existing and potential strategies.

cs.CL↗

arXiv2020

Predicting Unplanned Readmissions with Highly Unstructured Data

Deep learning techniques have been successfully applied to predict unplanned readmissions of patients in medical centers. The training data for these models is usually based on historical medical records that contain a significant amount of free-text from admission reports, referrals, exam notes, etc. Most of the models proposed so far are tailored to English text data and assume that electronic medical records follow standards common in developed countries. These two characteristics make them difficult to apply in developing countries that do not necessarily follow international standards for registering patient information, or that store text information in languages other than English. In this paper we propose a deep learning architecture for predicting unplanned readmissions that consumes data that is significantly less structured compared with previous models in the literature. We use it to present the first results for this task in a large clinical dataset that mainly contains Spanish text data. The dataset is composed of almost 10 years of records in a Chilean medical center. On this dataset, our model achieves results that are comparable to some of the most recent results obtained in US medical centers for the same task (0.76 AUROC).

cs.CL↗