arXiv subjects

Catherine Chen

Publications and source records attributed to Catherine Chen.

17 recordsLinked to original sources

arXiv2026

A Mechanistic Analysis of Gender Sensitivity in Dense Retrieval Models

While gender bias in dense retrieval models is well documented, with prior work showing that models often score male-gendered documents higher than female or neutral variants, the internal mechanisms producing these disparities are poorly understood. In this paper, we mechanistically analyze bi-encoder models to localize gender sensitivity, finding that the signal originates in input embeddings and propagates through a small set of late-layer attention heads that carry both gender and term-matching signals. Guided by these findings, we test steering interventions at both identified points and find distinct effects: embedding-level steering non-specifically neutralizes score differences, while attention-level steering produces directional shifts. Our findings provide a mechanistic basis for targeted debiasing and highlight the challenge of disentangling gender from relevance signals in shared model components.

cs.IR↗

arXiv2026

Forecasting Inflation with Microdata: An Adaptive Machine Learning Approach

Does microeconomic heterogeneity help to forecast aggregate inflation in a non-stationary environment? We develop a scan test for whether one forecast outperforms another, over an interval with unknown starting point and duration. To exploit any occasional forecasting power that the scan test detects, we design an adaptive machine learning pipeline. We encode the distribution of price changes into a high-dimensional vector, which we combine with a gradient boosted trees algorithm. We then combine this micro forecast with other benchmark forecasts, using an adaptive algorithm that makes use of the micro forecast only when it performs well. We apply the pipeline to UK microdata, with four main results. First, the micro forecast outperforms a univariate benchmark, but only in the volatile period after 2020. Second, the scan test detects periods of micro outperformance, so the micro forecast enters the combined forecast. Third, the combined forecast performs comparably to the univariate benchmark before 2020 and better at every horizon after 2020. Fourth, the value of microdata for the combined forecast materializes after 2020. We conclude that microdata are valuable for forecasting aggregate inflation, but only after large shocks.

econ.GN↗

arXiv2026

Adversarially Robust Control of Conditional Value-at-Risk via Rockafellar-Uryasev Conformal Inference

We present an online, distribution-free framework for controlling the Conditional Value-at-Risk (CVaR), extending conformal tail risk control to non-stationary and adversarial environments. Unlike classical risk control methods, which rely on stationarity or linearity of expectation, our approach provides provable safety guarantees for a nonlinear tail risk functional under arbitrary data-generating processes that may drift or shift strategically over time. By leveraging deep connections between conformal tail risk control, online learning, and the variational representation of CVaR introduced by Rockafellar and Uryasev, we develop a novel procedure for online CVaR control with adversarial regret guarantees. The proposed method operates without assumptions on the underlying data-generating process, making it broadly applicable in modern high-stakes deployment settings. We prove that the realized empirical CVaR is asymptotically controlled at the target level, and that the resulting control is asymptotically tight up to a finite-sample conservatism gap. We demonstrate the effectiveness of our approach on portfolio risk management and toxicity mitigation for Large Language Models (LLMs), where rare but catastrophic failures dominate system risk.

cs.LG↗

arXiv2026

Explainable Human Activity Recognition: A Unified Review of Concepts and Mechanisms

Human activity recognition (HAR) has become a key component of intelligent systems for healthcare monitoring, assistive living, smart environments, and human-computer interaction. Although deep learning has substantially improved HAR performance on multivariate sensor data, the resulting models often remain opaque, limiting trust, reliability, and real-world deployment. Explainable artificial intelligence (XAI) has therefore emerged as a critical direction for making HAR systems more transparent and human-centered. This paper presents a comprehensive review of explainable HAR methods across wearable, ambient, physiological, and multimodal sensing settings. We introduce a unified perspective that separates conceptual dimensions of explainability from algorithmic explanation mechanisms, reducing ambiguities in prior surveys. Building on this distinction, we present a mechanism-centric taxonomy of XAI-HAR methods covering major explanation paradigms. The review examines how these methods address the temporal, multimodal, and semantic complexities of HAR, and summarize their interpretability objectives, explanation targets, and limitations. In addition, we discuss current evaluation practices, highlight key challenges in achieving reliable and deployable XAI-HAR, and outline directions toward trustworthy activity recognition systems that better support human understanding and decision-making.

cs.LG↗

arXiv2026

RankSteer: Activation Steering for Pointwise LLM Ranking

Large language models (LLMs) have recently shown strong performance as zero-shot rankers, yet their effectiveness is highly sensitive to prompt formulation, particularly role-play instructions. Prior analyses suggest that role-related signals are encoded along activation channels that are largely separate from query-document representations, raising the possibility of steering ranking behavior directly at the activation level rather than through brittle prompt engineering. In this work, we propose RankSteer, a post-hoc activation steering framework for zero-shot pointwise LLM ranking. We characterize ranking behavior through three disentangled and steerable directions in representation space: a \textbf{decision direction} that maps hidden states to relevance scores, an \textbf{evidence direction} that captures relevance signals not directly exploited by the decision head, and a \textbf{role direction} that modulates model behavior without injecting relevance information. Using projection-based interventions at inference time, RankSteer jointly controls these directions to calibrate ranking behavior without modifying model weights or introducing explicit cross-document comparisons. Experiments on TREC DL 20 and multiple BEIR benchmarks show that RankSteer consistently improves ranking quality using only a small number of anchor queries, demonstrating that substantial ranking capacity remains under-utilized in pointwise LLM rankers. We further provide a geometric analysis revealing that steering improves ranking by stabilizing ranking geometry and reducing dispersion, offering new insight into how LLMs internally represent and calibrate relevance judgments.

cs.IR↗

arXiv2025

How role-play shapes relevance judgment in zero-shot LLM rankers

Large Language Models (LLMs) have emerged as promising zero-shot rankers, but their performance is highly sensitive to prompt formulation. In particular, role-play prompts, where the model is assigned a functional role or identity, often give more robust and accurate relevance rankings. However, the mechanisms and diversity of role-play effects remain underexplored, limiting both effective use and interpretability. In this work, we systematically examine how role-play variations influence zero-shot LLM rankers. We employ causal intervention techniques from mechanistic interpretability to trace how role-play information shapes relevance judgments in LLMs. Our analysis reveals that (1) careful formulation of role descriptions have a large effect on the ranking quality of the LLM; (2) role-play signals are predominantly encoded in early layers and communicate with task instructions in middle layers, while receiving limited interaction with query or document representations. Specifically, we identify a group of attention heads that encode information critical for role-conditioned relevance. These findings not only shed light on the inner workings of role-play in LLM ranking but also offer guidance for designing more effective prompts in IR and beyond, pointing toward broader opportunities for leveraging role-play in zero-shot applications.

cs.IR↗

arXiv2025

Pathway to Relevance: How Cross-Encoders Implement a Semantic Variant of BM25

Mechanistic interpretation has greatly contributed to a more detailed understanding of generative language models, enabling significant progress in identifying structures that implement key behaviors through interactions between internal components. In contrast, interpretability in information retrieval (IR) remains relatively coarse-grained, and much is still unknown as to how IR models determine whether a document is relevant to a query. In this work, we address this gap by mechanistically analyzing how one commonly used model, a cross-encoder, estimates relevance. We find that the model extracts traditional relevance signals, such as term frequency and inverse document frequency, in early-to-middle layers. These concepts are then combined in later layers, similar to the well-known probabilistic ranking function, BM25. Overall, our analysis offers a more nuanced understanding of how IR models compute relevance. Isolating these components lays the groundwork for future interventions that could enhance transparency, mitigate safety risks, and improve scalability.

cs.IR↗

arXiv2025

MechIR: A Mechanistic Interpretability Framework for Information Retrieval

Mechanistic interpretability is an emerging diagnostic approach for neural models that has gained traction in broader natural language processing domains. This paradigm aims to provide attribution to components of neural systems where causal relationships between hidden layers and output were previously uninterpretable. As the use of neural models in IR for retrieval and evaluation becomes ubiquitous, we need to ensure that we can interpret why a model produces a given output for both transparency and the betterment of systems. This work comprises a flexible framework for diagnostic analysis and intervention within these highly parametric neural systems specifically tailored for IR tasks and architectures. In providing such a framework, we look to facilitate further research in interpretable IR with a broader scope for practical interventions derived from mechanistic interpretability. We provide preliminary analysis and look to demonstrate our framework through an axiomatic lens to show its applications and ease of use for those IR practitioners inexperienced in this emerging paradigm.

cs.IR↗

arXiv2024

Political-LLM: Large Language Models in Political Science

In recent years, large language models (LLMs) have been widely adopted in political science tasks such as election prediction, sentiment analysis, policy impact assessment, and misinformation detection. Meanwhile, the need to systematically understand how LLMs can further revolutionize the field also becomes urgent. In this work, we--a multidisciplinary team of researchers spanning computer science and political science--present the first principled framework termed Political-LLM to advance the comprehensive understanding of integrating LLMs into computational political science. Specifically, we first introduce a fundamental taxonomy classifying the existing explorations into two perspectives: political science and computational methodologies. In particular, from the political science perspective, we highlight the role of LLMs in automating predictive and generative tasks, simulating behavior dynamics, and improving causal inference through tools like counterfactual generation; from a computational perspective, we introduce advancements in data preparation, fine-tuning, and evaluation methods for LLMs that are tailored to political contexts. We identify key challenges and future directions, emphasizing the development of domain-specific datasets, addressing issues of bias and fairness, incorporating human expertise, and redefining evaluation criteria to align with the unique requirements of computational political science. Political-LLM seeks to serve as a guidebook for researchers to foster an informed, ethical, and impactful use of Artificial Intelligence in political science. Our online resource is available at: http://political-llm.org/.

cs.CL↗

arXiv2024

Axiomatic Causal Interventions for Reverse Engineering Relevance Computation in Neural Retrieval Models

Neural models have demonstrated remarkable performance across diverse ranking tasks. However, the processes and internal mechanisms along which they determine relevance are still largely unknown. Existing approaches for analyzing neural ranker behavior with respect to IR properties rely either on assessing overall model behavior or employing probing methods that may offer an incomplete understanding of causal mechanisms. To provide a more granular understanding of internal model decision-making processes, we propose the use of causal interventions to reverse engineer neural rankers, and demonstrate how mechanistic interpretability methods can be used to isolate components satisfying term-frequency axioms within a ranking model. We identify a group of attention heads that detect duplicate tokens in earlier layers of the model, then communicate with downstream heads to compute overall document relevance. More generally, we propose that this style of mechanistic analysis opens up avenues for reverse engineering the processes neural retrieval models use to compute relevance. This work aims to initiate granular interpretability efforts that will not only benefit retrieval model development and training, but ultimately ensure safer deployment of these models.

cs.IR↗

arXiv2023

Outlier Dimensions Encode Task-Specific Knowledge

Representations from large language models (LLMs) are known to be dominated by a small subset of dimensions with exceedingly high variance. Previous works have argued that although ablating these outlier dimensions in LLM representations hurts downstream performance, outlier dimensions are detrimental to the representational quality of embeddings. In this study, we investigate how fine-tuning impacts outlier dimensions and show that 1) outlier dimensions that occur in pre-training persist in fine-tuned models and 2) a single outlier dimension can complete downstream tasks with a minimal error rate. Our results suggest that outlier dimensions can encode crucial task-specific knowledge and that the value of a representation in a single outlier dimension drives downstream model decisions.

cs.CL↗

arXiv2023

SSE: A Metric for Evaluating Search System Explainability

Explainable Information Retrieval (XIR) is a growing research area focused on enhancing transparency and trustworthiness of the complex decision-making processes taking place in modern information retrieval systems. While there has been progress in developing XIR systems, empirical evaluation tools to assess the degree of explainability attained by such systems are lacking. To close this gap and gain insights into the true merit of XIR systems, we extend existing insights from a factor analysis of search explainability to introduce SSE (Search System Explainability), an evaluation metric for XIR search systems. Through a crowdsourced user study, we demonstrate SSE's ability to distinguish between explainable and non-explainable systems, showing that systems with higher scores indeed indicate greater interpretability. Additionally, we observe comparable perceived temporal demand and performance levels between non-native and native English speakers. We hope that aside from these concrete contributions to XIR, this line of work will serve as a blueprint for similar explainability evaluation efforts in other domains of machine learning and natural language processing.

cs.IR↗

arXiv2023

Are Layout-Infused Language Models Robust to Layout Distribution Shifts? A Case Study with Scientific Documents

Recent work has shown that infusing layout features into language models (LMs) improves processing of visually-rich documents such as scientific papers. Layout-infused LMs are often evaluated on documents with familiar layout features (e.g., papers from the same publisher), but in practice models encounter documents with unfamiliar distributions of layout features, such as new combinations of text sizes and styles, or new spatial configurations of textual elements. In this work we test whether layout-infused LMs are robust to layout distribution shifts. As a case study we use the task of scientific document structure recovery, segmenting a scientific paper into its structural categories (e.g., "title", "caption", "reference"). To emulate distribution shifts that occur in practice we re-partition the GROTOAP2 dataset. We find that under layout distribution shifts model performance degrades by up to 20 F1. Simple training strategies, such as increasing training diversity, can reduce this degradation by over 35% relative F1; however, models fail to reach in-distribution performance in any tested out-of-distribution conditions. This work highlights the need to consider layout distribution shifts during model evaluation, and presents a methodology for conducting such evaluations.

cs.CL↗

arXiv2022

Re-evaluating the Need for Multimodal Signals in Unsupervised Grammar Induction

Are multimodal inputs necessary for grammar induction? Recent work has shown that multimodal training inputs can improve grammar induction. However, these improvements are based on comparisons to weak text-only baselines that were trained on relatively little textual data. To determine whether multimodal inputs are needed in regimes with large amounts of textual training data, we design a stronger text-only baseline, which we refer to as LC-PCFG. LC-PCFG is a C-PFCG that incorporates em-beddings from text-only large language models (LLMs). We use a fixed grammar family to directly compare LC-PCFG to various multi-modal grammar induction methods. We compare performance on four benchmark datasets. LC-PCFG provides an up to 17% relative improvement in Corpus-F1 compared to state-of-the-art multimodal grammar induction methods. LC-PCFG is also more computationally efficient, providing an up to 85% reduction in parameter count and 8.8x reduction in training time compared to multimodal approaches. These results suggest that multimodal inputs may not be necessary for grammar induction, and emphasize the importance of strong vision-free baselines for evaluating the benefit of multimodal approaches.

cs.CL↗

arXiv2022

Evaluating Search System Explainability with Psychometrics and Crowdsourcing

As information retrieval (IR) systems, such as search engines and conversational agents, become ubiquitous in various domains, the need for transparent and explainable systems grows to ensure accountability, fairness, and unbiased results. Despite recent advances in explainable AI and IR techniques, there is no consensus on the definition of explainability. Existing approaches often treat it as a singular notion, disregarding the multidimensional definition postulated in the literature. In this paper, we use psychometrics and crowdsourcing to identify human-centered factors of explainability in Web search systems and introduce SSE (Search System Explainability), an evaluation metric for explainable IR (XIR) search systems. In a crowdsourced user study, we demonstrate SSE's ability to distinguish between explainable and non-explainable systems, showing that systems with higher scores indeed indicate greater interpretability. We hope that aside from these concrete contributions to XIR, this line of work will serve as a blueprint for similar explainability evaluation efforts in other domains of machine learning and natural language processing.

cs.IR↗

arXiv2021

Constructing Taxonomies from Pretrained Language Models

We present a method for constructing taxonomic trees (e.g., WordNet) using pretrained language models. Our approach is composed of two modules, one that predicts parenthood relations and another that reconciles those predictions into trees. The parenthood prediction module produces likelihood scores for each potential parent-child pair, creating a graph of parent-child relation scores. The tree reconciliation module treats the task as a graph optimization problem and outputs the maximum spanning tree of this graph. We train our model on subtrees sampled from WordNet, and test on non-overlapping WordNet subtrees. We show that incorporating web-retrieved glosses can further improve performance. On the task of constructing subtrees of English WordNet, the model achieves 66.7 ancestor F1, a 20.0% relative increase over the previous best published result on this task. In addition, we convert the original English dataset into nine other languages using Open Multilingual WordNet and extend our results across these languages.

cs.CL↗

arXiv2020

Learning to Perform Role-Filler Binding with Schematic Knowledge

Through specific experiences, humans learn relationships underlying the structure of events in the world. Schema theory suggests that we organize this information in mental frameworks called "schemata," which represent our knowledge of the structure of the world. Generalizing knowledge of structural relationships to new situations requires role-filler binding, the ability to associate specific "fillers" with abstract "roles." For instance, when we hear the sentence "Alice ordered a tea from Bob," the role-filler bindings "Alice:customer," "tea:drink," and "Bob:barista" allow us to understand and make inferences about the sentence. We can perform these bindings for arbitrary fillers -- we understand this sentence even if we have never heard the names "Alice," "tea," or "Bob" before. In this work, we define a model as capable of performing role-filler binding if it can recall arbitrary fillers corresponding to a specified role, even when these pairings violate correlations seen during training. Previous work found that models can learn this ability when explicitly told what the roles and fillers are, or when given fillers seen during training. We show that networks with external memory can learn these relationships with fillers not seen during training and without explicitly labeled role-filler bindings, and show that analyses inspired by neural decoding can provide a means of understanding what the networks have learned.

cs.AI↗