Navita Goyal

Navita Goyal, Hal Daumé

Model steering, which involves intervening on hidden representations at inference time, has emerged as a lightweight alternative to finetuning for precisely controlling large language models. While steering efficacy has been widely studied, evaluations of whether interventions alter only the intended property remain limited, especially with respect to unintended changes in behaviors related to the target property. We call this notion specificity. We propose a framework that distinguishes three dimensions of specificity: general (preserving fluency and unrelated abilities), control (preserving related control properties), and robustness (preserving control properties under distribution shifts). We study two safety-critical use cases: steering models to reduce overrefusal and faithfulness hallucinations, and show that while steering achieves high efficacy and largely maintains general and control specificity, it consistently fails to preserve robustness specificity. In the case of overrefusal steering, for example, all steering methods reduce overrefusal without harming general abilities and refusal on harmful queries; however, they substantially increase vulnerability to jailbreaks. Our work provides the first systematic evaluation of specificity in model steering, showing that standard efficacy and specificity checks are insufficient, because without robustness evaluation, steering methods may appear reliable even when they compromise model safety.

Chenglei Si, Navita Goyal, Sherry Tongshuang Wu et al.

Large Language Models (LLMs) are increasingly used for accessing information on the web. Their truthfulness and factuality are thus of great interest. To help users make the right decisions about the information they get, LLMs should not only provide information but also help users fact-check it. Our experiments with 80 crowdworkers compare language models with search engines (information retrieval systems) at facilitating fact-checking. We prompt LLMs to validate a given claim and provide corresponding explanations. Users reading LLM explanations are significantly more efficient than those using search engines while achieving similar accuracy. However, they over-rely on the LLMs when the explanation is wrong. To reduce over-reliance on LLMs, we ask LLMs to provide contrastive information - explain both why the claim is true and false, and then we present both sides of the explanation to users. This contrastive explanation mitigates users' over-reliance on LLMs, but cannot significantly outperform search engines. Further, showing both search engine results and LLM explanations offers no complementary benefits compared to search engines alone. Taken together, our study highlights that natural language explanations by LLMs may not be a reliable replacement for reading the retrieved passages, especially in high-stakes settings where over-relying on wrong AI explanations could lead to critical consequences.

Atanu R Sinha, Navita Goyal, Sunny Dhamnani et al.

Cognitive biases are mental shortcuts humans use in dealing with information and the environment, and which result in biased actions and behaviors (or, actions), unbeknownst to themselves. Biases take many forms, with cognitive biases occupying a central role that inflicts fairness, accountability, transparency, ethics, law, medicine, and discrimination. Detection of biases is considered a necessary step toward their mitigation. Herein, we focus on two cognitive biases - anchoring and recency. The recognition of cognitive bias in computer science is largely in the domain of information retrieval, and bias is identified at an aggregate level with the help of annotated data. Proposing a different direction for bias detection, we offer a principled approach along with Machine Learning to detect these two cognitive biases from Web logs of users' actions. Our individual user level detection makes it truly personalized, and does not rely on annotated data. Instead, we start with two basic principles established in cognitive psychology, use modified training of an attention network, and interpret attention weights in a novel way according to those principles, to infer and distinguish between these two biases. The personalized approach allows detection for specific users who are susceptible to these biases when performing their tasks, and can help build awareness among them so as to undertake bias mitigation.

Navita Goyal, Connor Baumler, Tin Nguyen et al.

AI systems have been known to amplify biases in real-world data. Explanations may help human-AI teams address these biases for fairer decision-making. Typically, explanations focus on salient input features. If a model is biased against some protected group, explanations may include features that demonstrate this bias, but when biases are realized through proxy features, the relationship between this proxy feature and the protected one may be less clear to a human. In this work, we study the effect of the presence of protected and proxy features on participants' perception of model fairness and their ability to improve demographic parity over an AI alone. Further, we examine how different treatments -- explanations, model bias disclosure and proxy correlation disclosure -- affect fairness perception and parity. We find that explanations help people detect direct but not indirect biases. Additionally, regardless of bias type, explanations tend to increase agreement with model biases. Disclosures can help mitigate this effect for indirect biases, improving both unfairness recognition and decision-making fairness. We hope that our findings can help guide further research into advancing explanations in support of fair human-AI decision-making.

Eleftheria Briakou, Navita Goyal, Marine Carpuat

Explainable NLP techniques primarily explain by answering "Which tokens in the input are responsible for this prediction?''. We argue that for NLP models that make predictions by comparing two input texts, it is more useful to explain by answering "What differences between the two inputs explain this prediction?''. We introduce a technique to generate contrastive highlights that explain the predictions of a semantic divergence model via phrase-alignment-guided erasure. We show that the resulting highlights match human rationales of cross-lingual semantic differences better than popular post-hoc saliency techniques and that they successfully help people detect fine-grained meaning differences in human translations and critical machine translation errors.

Navita Goyal, Ivan Stelmakh, Nihar Shah et al.

A large host of scientific journals and conferences solicit peer reviews from multiple reviewers for the same submission, aiming to gather a broader range of perspectives and mitigate individual biases. In this work, we reflect on the role of diversity in the slate of reviewers assigned to evaluate a submitted paper as a factor in diversifying perspectives and improving the utility of the peer-review process. We propose two measures for assessing review utility: review coverage -- reviews should cover most contents of the paper -- and review redundancy -- reviews should add information not already present in other reviews. We hypothesize that reviews from diverse reviewers will exhibit high coverage and low redundancy. We conduct a causal study of different measures of reviewer diversity on review coverage and redundancy using observational data from a peer-reviewed conference with approximately 5,000 submitted papers. Our study reveals disparate effects of different diversity measures on review coverage and redundancy. Our study finds that assigning a group of reviewers that are topically diverse, have different seniority levels, or have distinct publication networks leads to broader coverage of the paper or review criteria, but we find no evidence of an increase in coverage for reviewer slates with reviewers from diverse organizations or geographical locations. Reviewers from different organizations, seniority levels, topics, or publications networks (all except geographical diversity) lead to a decrease in redundancy in reviews. Furthermore, publication network-based diversity alone also helps bring in varying perspectives (that is, low redundancy), even within specific review criteria. Our study adopts a group decision-making perspective for reviewer assignments in peer review and suggests dimensions of diversity that can help guide the reviewer assignment process.

Navita Goyal, Eleftheria Briakou, Amanda Liu et al.

NLP systems have shown impressive performance at answering questions by retrieving relevant context. However, with the increasingly large models, it is impossible and often undesirable to constrain models' knowledge or reasoning to only the retrieved context. This leads to a mismatch between the information that the models access to derive the answer and the information that is available to the user to assess the model predicted answer. In this work, we study how users interact with QA systems in the absence of sufficient information to assess their predictions. Further, we ask whether adding the requisite background helps mitigate users' over-reliance on predictions. Our study reveals that users rely on model predictions even in the absence of sufficient information needed to assess the model's correctness. Providing the relevant background, however, helps users better catch model errors, reducing over-reliance on incorrect predictions. On the flip side, background information also increases users' confidence in their accurate as well as inaccurate judgments. Our work highlights that supporting users' verification of QA predictions is an important, yet challenging, problem.

Navita Goyal, Roodram Paneri, Ayush Agarwal et al.

Content is created for a well-defined purpose, often described by a metric or signal represented in the form of structured information. The relationship between the goal (metrics) of target content and the content itself is non-trivial. While large-scale language models show promising text generation capabilities, guiding the generated text with external metrics is challenging. These metrics and content tend to have inherent relationships and not all of them may be of consequence. We introduce CaM-Gen: Causally aware Generative Networks guided by user-defined target metrics incorporating the causal relationships between the metric and content features. We leverage causal inference techniques to identify causally significant aspects of a text that lead to the target metric and then explicitly guide generative models towards these by a feedback mechanism. We propose this mechanism for variational autoencoder and Transformer-based generative models. The proposed models beat baselines in terms of the target metric control while maintaining fluency and language quality of the generated text. To the best of our knowledge, this is one of the early attempts at controlled generation incorporating a metric guide using causal inference.

Navita Goyal, Balaji Vasan Srinivasan, Anandhavelu Natarajan et al.

Style transfer has been widely explored in natural language generation with non-parallel corpus by directly or indirectly extracting a notion of style from source and target domain corpus. A common shortcoming of existing approaches is the prerequisite of joint annotations across all the stylistic dimensions under consideration. Availability of such dataset across a combination of styles limits the extension of these setups to multiple style dimensions. While cascading single-dimensional models across multiple styles is a possibility, it suffers from content loss, especially when the style dimensions are not completely independent of each other. In our work, we relax this requirement of jointly annotated data across multiple styles by using independently acquired data across different style dimensions without any additional annotations. We initialize an encoder-decoder setup with transformer-based language model pre-trained on a generic corpus and enhance its re-writing capability to multiple target style dimensions by employing multiple style-aware language models as discriminators. Through quantitative and qualitative evaluation, we show the ability of our model to control styles across multiple style dimensions while preserving content of the input text. We compare it against baselines involving cascaded state-of-the-art uni-dimensional style transfer models.