Bhargavi Paranjape

Bhargavi Paranjape, Scott Lundberg, Sameer Singh et al. · microsoft-research, uw

Large language models (LLMs) can perform complex reasoning in few- and zero-shot settings by generating intermediate chain of thought (CoT) reasoning steps. Further, each reasoning step can rely on external tools to support computation beyond the core LLM capabilities (e.g. search/running code). Prior work on CoT prompting and tool use typically requires hand-crafting task-specific demonstrations and carefully scripted interleaving of model generations with tool use. We introduce Automatic Reasoning and Tool-use (ART), a framework that uses frozen LLMs to automatically generate intermediate reasoning steps as a program. Given a new task to solve, ART selects demonstrations of multi-step reasoning and tool use from a task library. At test time, ART seamlessly pauses generation whenever external tools are called, and integrates their output before resuming generation. ART achieves a substantial improvement over few-shot prompting and automatic CoT on unseen tasks in the BigBench and MMLU benchmarks, and matches performance of hand-crafted CoT prompts on a majority of these tasks. ART is also extensible, and makes it easy for humans to improve performance by correcting errors in task-specific programs or incorporating new tools, which we demonstrate by drastically improving performance on select tasks with minimal human intervention.

Aaron Grattafiori, Abhimanyu Dubey, Abhinav Jauhri et al. · allen-ai, berkeley

Modern artificial intelligence (AI) systems are powered by foundation models. This paper presents a new set of foundation models, called Llama 3. It is a herd of language models that natively support multilinguality, coding, reasoning, and tool usage. Our largest model is a dense Transformer with 405B parameters and a context window of up to 128K tokens. This paper presents an extensive empirical evaluation of Llama 3. We find that Llama 3 delivers comparable quality to leading language models such as GPT-4 on a plethora of tasks. We publicly release Llama 3, including pre-trained and post-trained versions of the 405B parameter language model and our Llama Guard 3 model for input and output safety. The paper also presents the results of experiments in which we integrate image, video, and speech capabilities into Llama 3 via a compositional approach. We observe this approach performs competitively with the state-of-the-art on image, video, and speech recognition tasks. The resulting models are not yet being broadly released as they are still under development.

Tanay Dixit, Bhargavi Paranjape, Hannaneh Hajishirzi et al. · uw

Counterfactual data augmentation (CDA) -- i.e., adding minimally perturbed inputs during training -- helps reduce model reliance on spurious correlations and improves generalization to out-of-distribution (OOD) data. Prior work on generating counterfactuals only considered restricted classes of perturbations, limiting their effectiveness. We present COunterfactual Generation via Retrieval and Editing (CORE), a retrieval-augmented generation framework for creating diverse counterfactual perturbations for CDA. For each training example, CORE first performs a dense retrieval over a task-related unlabeled text corpus using a learned bi-encoder and extracts relevant counterfactual excerpts. CORE then incorporates these into prompts to a large language model with few-shot learning capabilities, for counterfactual editing. Conditioning language model edits on naturally occurring data results in diverse perturbations. Experiments on natural language inference and sentiment analysis benchmarks show that CORE counterfactuals are more effective at improving generalization to OOD data compared to other DA approaches. We also show that the CORE retrieval framework can be used to encourage diversity in manually authored perturbations

Bhargavi Paranjape, Pradeep Dasigi, Vivek Srikumar et al. · uw

Models trained via empirical risk minimization (ERM) are known to rely on spurious correlations between labels and task-independent input features, resulting in poor generalization to distributional shifts. Group distributionally robust optimization (G-DRO) can alleviate this problem by minimizing the worst-case loss over a set of pre-defined groups over training data. G-DRO successfully improves performance of the worst-group, where the correlation does not hold. However, G-DRO assumes that the spurious correlations and associated worst groups are known in advance, making it challenging to apply it to new tasks with potentially multiple unknown spurious correlations. We propose AGRO -- Adversarial Group discovery for Distributionally Robust Optimization -- an end-to-end approach that jointly identifies error-prone groups and improves accuracy on them. AGRO equips G-DRO with an adversarial slicing model to find a group assignment for training examples which maximizes worst-case loss over the discovered groups. On the WILDS benchmark, AGRO results in 8% higher model performance on average on known worst-groups, compared to prior group discovery approaches used with G-DRO. AGRO also improves out-of-distribution performance on SST2, QQP, and MS-COCO -- datasets where potential spurious correlations are as yet uncharacterized. Human evaluation of ARGO groups shows that they contain well-defined, yet previously unstudied spurious correlations that lead to model errors.

Shuyue Stella Li, Bhargavi Paranjape, Kerem Oktar et al.

User preferences evolve across months of interaction, and tracking them requires inferring when a stated preference has been changed by a subsequent life event. We define this problem as long-horizon personalization and observe that progress on it is limited by data availability and measurement, with no existing resource providing both naturalistic long-horizon interactions and the ground-truth provenance needed to diagnose why models fail. We introduce a data generator that produces conversations from a structured mental state graph, yielding ground-truth provenance for every preference change across 6-month timelines, and from it construct HorizonBench, a benchmark of 4,245 items from 360 simulated users with 6-month conversation histories averaging ~4,300 turns and ~163K tokens. HorizonBench provides a testbed for long-context modeling, memory-augmented architectures, theory-of-mind reasoning, and user modeling. Across 25 frontier models, the best model reaches 52.8% and most score at or below the 20% chance baseline. When these models err on evolved preferences, over a third of the time they select the user's originally stated value without tracking the updated user state. This belief-update failure persists across context lengths and expression explicitness levels, identifying state-tracking capability as the primary bottleneck for long-horizon personalization.

Yanai Elazar, Bhargavi Paranjape, Hao Peng et al.

The inevitable appearance of spurious correlations in training datasets hurts the generalization of NLP models on unseen data. Previous work has found that datasets with paired inputs are prone to correlations between a specific part of the input (e.g., the hypothesis in NLI) and the label; consequently, models trained only on those outperform chance. Are these correlations picked up by models trained on the full input data? To address this question, we propose a new evaluation method, Counterfactual Attentiveness Test (CAT). CAT uses counterfactuals by replacing part of the input with its counterpart from a different example (subject to some restrictions), expecting an attentive model to change its prediction. Using CAT, we systematically investigate established supervised and in-context learning models on ten datasets spanning four tasks: natural language inference, reading comprehension, paraphrase detection, and visual & language reasoning. CAT reveals that reliance on such correlations is mainly data-dependent. Surprisingly, we find that GPT3 becomes less attentive with an increased number of demonstrations, while its accuracy on the test data improves. Our results demonstrate that augmenting training or demonstration data with counterfactuals is effective in improving models' attentiveness. We show that models' attentiveness measured by CAT reveals different conclusions from solely measuring correlations in data.

Alex Warstadt, Aaron Mueller, Leshem Choshen et al. · ibm-research

Children can acquire language from less than 100 million words of input. Large language models are far less data-efficient: they typically require 3 or 4 orders of magnitude more data and still do not perform as well as humans on many evaluations. These intensive resource demands limit the ability of researchers to train new models and use existing models as developmentally plausible cognitive models. The BabyLM Challenge is a communal effort in which participants compete to optimize language model training on a fixed data budget. Submissions are compared on various evaluation tasks targeting grammatical ability, downstream task performance, and generalization. Participants can submit to up to three tracks with progressively looser data restrictions. From over 30 submissions, we extract concrete recommendations on how best to train data-efficient language models, and on where future efforts should (and perhaps should not) focus. The winning submissions using the LTG-BERT architecture (Samuel et al., 2023) outperformed models trained on trillions of words. Other submissions achieved strong results through training on shorter input sequences or training a student model on a pretrained teacher. Curriculum learning attempts, which accounted for a large number of submissions, were largely unsuccessful, though some showed modest improvements.

Joongwon Kim, Bhargavi Paranjape, Tushar Khot et al.

Language agents perform complex tasks by using tools to execute each step precisely. However, most existing agents are based on proprietary models or designed to target specific tasks, such as mathematics or multi-hop question answering. We introduce Husky, a holistic, open-source language agent that learns to reason over a unified action space to address a diverse set of complex tasks involving numerical, tabular, and knowledge-based reasoning. Husky iterates between two stages: 1) generating the next action to take towards solving a given task and 2) executing the action using expert models and updating the current solution state. We identify a thorough ontology of actions for addressing complex tasks and curate high-quality data to train expert models for executing these actions. Our experiments show that Husky outperforms prior language agents across 14 evaluation datasets. Moreover, we introduce HuskyQA, a new evaluation set which stress tests language agents for mixed-tool reasoning, with a focus on retrieving missing knowledge and performing numerical reasoning. Despite using 7B models, Husky matches or even exceeds frontier LMs such as GPT-4 on these tasks, showcasing the efficacy of our holistic approach in addressing complex reasoning problems. Our code and models are available at https://github.com/agent-husky/Husky-v1.

William Held, Bhargavi Paranjape, Punit Singh Koura et al. · gatech

Large Language Models improve with increasing amounts of high-quality training data. However, leveraging larger datasets requires balancing quality, quantity, and diversity across sources. After evaluating nine baseline methods under both compute- and data-constrained scenarios, we find token-count heuristics outperform manual and learned mixes, indicating that simple approaches accounting for dataset size and diversity are surprisingly effective. Building on this insight, we propose two complementary approaches: UtiliMax, which extends token-based heuristics by incorporating utility estimates from reduced-scale ablations, achieving up to a 10.6x speedup over manual baselines; and Model Estimated Data Utility (MEDU), which leverages LLMs to estimate data utility from small samples, matching ablation-based performance while reducing computational requirements by $\sim$200x. Together, these approaches establish a new framework for automated, compute-efficient data mixing that is robust across training regimes.

Qingqing Cao, Bhargavi Paranjape, Hannaneh Hajishirzi

Large-scale vision language (VL) models use Transformers to perform cross-modal interactions between the input text and image. These cross-modal interactions are computationally expensive and memory-intensive due to the quadratic complexity of processing the input image and text. We present PuMer: a token reduction framework that uses text-informed Pruning and modality-aware Merging strategies to progressively reduce the tokens of input image and text, improving model inference speed and reducing memory footprint. PuMer learns to keep salient image tokens related to the input text and merges similar textual and visual tokens by adding lightweight token reducer modules at several cross-modal layers in the VL model. Training PuMer is mostly the same as finetuning the original VL model but faster. Our evaluation for two vision language models on four downstream VL tasks shows PuMer increases inference throughput by up to 2x and reduces memory footprint by over 50% while incurring less than a 1% accuracy drop.

Bhargavi Paranjape, Matthew Lamm, Ian Tenney

Deep NLP models have been shown to learn spurious correlations, leaving them brittle to input perturbations. Recent work has shown that counterfactual or contrastive data -- i.e. minimally perturbed inputs -- can reveal these weaknesses, and that data augmentation using counterfactuals can help ameliorate them. Proposed techniques for generating counterfactuals rely on human annotations, perturbations based on simple heuristics, and meaning representation frameworks. We focus on the task of creating counterfactuals for question answering, which presents unique challenges related to world knowledge, semantic diversity, and answerability. To address these challenges, we develop a Retrieve-Generate-Filter(RGF) technique to create counterfactual evaluation and training data with minimal human supervision. Using an open-domain QA framework and question generation model trained on original task data, we create counterfactuals that are fluent, semantically diverse, and automatically labeled. Data augmentation with RGF counterfactuals improves performance on out-of-domain and challenging evaluation sets over and above existing methods, in both the reading comprehension and open-domain QA settings. Moreover, we find that RGF data leads to significant improvements in a model's robustness to local perturbations.

Bhargavi Paranjape, Julian Michael, Marjan Ghazvininejad et al.

Many commonsense reasoning NLP tasks involve choosing between one or more possible answers to a question or prompt based on knowledge that is often implicit. Large pretrained language models (PLMs) can achieve near-human performance on such tasks, while providing little human-interpretable evidence of the underlying reasoning they use. In this work, we show how to use these same models to generate such evidence: inspired by the contrastive nature of human explanations, we use PLMs to complete explanation prompts which contrast alternatives according to the key attribute(s) required to justify the correct answer (for example, peanuts are usually salty while raisins are sweet). Conditioning model decisions on these explanations improves performance on two commonsense reasoning benchmarks, as compared to previous non-contrastive alternatives. These explanations are also judged by humans to be more relevant for solving the task, and facilitate a novel method to evaluate explanation faithfulfness.

Haoran Li, Arash Einolghozati, Srinivasan Iyer et al.

Current abstractive summarization systems outperform their extractive counterparts, but their widespread adoption is inhibited by the inherent lack of interpretability. To achieve the best of both worlds, we propose EASE, an extractive-abstractive framework for evidence-based text generation and apply it to document summarization. We present an explainable summarization system based on the Information Bottleneck principle that is jointly trained for extraction and abstraction in an end-to-end fashion. Inspired by previous research that humans use a two-stage framework to summarize long documents (Jing and McKeown, 2000), our framework first extracts a pre-defined amount of evidence spans as explanations and then generates a summary using only the evidence. Using automatic and human evaluations, we show that explanations from our framework are more relevant than simple baselines, without substantially sacrificing the quality of the generated summary.

Kushal Lakhotia, Bhargavi Paranjape, Asish Ghoshal et al.

Natural language (NL) explanations of model predictions are gaining popularity as a means to understand and verify decisions made by large black-box pre-trained models, for NLP tasks such as Question Answering (QA) and Fact Verification. Recently, pre-trained sequence to sequence (seq2seq) models have proven to be very effective in jointly making predictions, as well as generating NL explanations. However, these models have many shortcomings; they can fabricate explanations even for incorrect predictions, they are difficult to adapt to long input documents, and their training requires a large amount of labeled data. In this paper, we develop FiD-Ex, which addresses these shortcomings for seq2seq models by: 1) introducing sentence markers to eliminate explanation fabrication by encouraging extractive generation, 2) using the fusion-in-decoder architecture to handle long input contexts, and 3) intermediate fine-tuning on re-structured open domain QA datasets to improve few-shot performance. FiD-Ex significantly improves over prior work in terms of explanation metrics and task accuracy, on multiple tasks from the ERASER explainability benchmark, both in the fully supervised and in the few-shot settings.

Bhargavi Paranjape, Mandar Joshi, John Thickstun et al.

Decisions of complex language understanding models can be rationalized by limiting their inputs to a relevant subsequence of the original text. A rationale should be as concise as possible without significantly degrading task performance, but this balance can be difficult to achieve in practice. In this paper, we show that it is possible to better manage this trade-off by optimizing a bound on the Information Bottleneck (IB) objective. Our fully unsupervised approach jointly learns an explainer that predicts sparse binary masks over sentences, and an end-task predictor that considers only the extracted rationale. Using IB, we derive a learning objective that allows direct control of mask sparsity levels through a tunable sparse prior. Experiments on ERASER benchmark tasks demonstrate significant gains over norm-minimization techniques for both task performance and agreement with human rationales. Furthermore, we find that in the semi-supervised setting, a modest amount of gold rationales (25% of training examples) closes the gap with a model that uses the full input.

Alankar Jain, Bhargavi Paranjape, Zachary C. Lipton

Although over 100 languages are supported by strong off-the-shelf machine translation systems, only a subset of them possess large annotated corpora for named entity recognition. Motivated by this fact, we leverage machine translation to improve annotation-projection approaches to cross-lingual named entity recognition. We propose a system that improves over prior entity-projection methods by: (a) leveraging machine translation systems twice: first for translating sentences and subsequently for translating entities; (b) matching entities based on orthographic and phonetic similarity; and (c) identifying matches based on distributional statistics derived from the dataset. Our approach improves upon current state-of-the-art methods for cross-lingual named entity recognition on 5 diverse languages by an average of 4.1 points. Further, our method achieves state-of-the-art F_1 scores for Armenian, outperforming even a monolingual model trained on Armenian source data.

Aditi Chaudhary, Bhargavi Paranjape, Michiel de Jong

Motivated by recent evidence pointing out the fragility of high-performing span prediction models, we direct our attention to multiple choice reading comprehension. In particular, this work introduces a novel method for improving answer selection on long documents through weighted global normalization of predictions over portions of the documents. We show that applying our method to a span prediction model adapted for answer selection helps model performance on long summaries from NarrativeQA, a challenging reading comprehension dataset with an answer selection task, and we strongly improve on the task baseline performance by +36.2 Mean Reciprocal Rank.

Dheeraj Mekala, Vivek Gupta, Bhargavi Paranjape et al.

We present a feature vector formation technique for documents - Sparse Composite Document Vector (SCDV) - which overcomes several shortcomings of the current distributional paragraph vector representations that are widely used for text representation. In SCDV, word embedding's are clustered to capture multiple semantic contexts in which words occur. They are then chained together to form document topic-vectors that can express complex, multi-topic documents. Through extensive experiments on multi-class and multi-label classification tasks, we outperform the previous state-of-the-art method, NTSG (Liu et al., 2015a). We also show that SCDV embedding's perform well on heterogeneous tasks like Topic Coherence, context-sensitive Learning and Information Retrieval. Moreover, we achieve significant reduction in training and prediction times compared to other representation methods. SCDV achieves best of both worlds - better performance with lower time and space complexity.

Abhijnan Chakraborty, Bhargavi Paranjape, Sourya Kakarla et al.

Most of the online news media outlets rely heavily on the revenues generated from the clicks made by their readers, and due to the presence of numerous such outlets, they need to compete with each other for reader attention. To attract the readers to click on an article and subsequently visit the media site, the outlets often come up with catchy headlines accompanying the article links, which lure the readers to click on the link. Such headlines are known as Clickbaits. While these baits may trick the readers into clicking, in the long run, clickbaits usually don't live up to the expectation of the readers, and leave them disappointed. In this work, we attempt to automatically detect clickbaits and then build a browser extension which warns the readers of different media sites about the possibility of being baited by such headlines. The extension also offers each reader an option to block clickbaits she doesn't want to see. Then, using such reader choices, the extension automatically blocks similar clickbaits during her future visits. We run extensive offline and online experiments across multiple media sites and find that the proposed clickbait detection and the personalized blocking approaches perform very well achieving 93% accuracy in detecting and 89% accuracy in blocking clickbaits.