We introduce AbGen, the first benchmark designed to evaluate the capabilities of LLMs in designing ablation studies for scientific research. AbGen consists of 2,000 expert-annotated examples derived from 677 NLP papers. In this benchmark, LLMs are tasked with generating detailed ablation study designs for a specified module or process based on the given research context. Our evaluation of leading LLMs, such as GPT-4o and Llama-3.1, highlights a significant performance gap between these models and human experts in terms of the importance, faithfulness, and soundness of the ablation study designs. Moreover, we demonstrate that current automated evaluation methods are not reliable for our task, as they show a significant discrepancy when compared to human assessment. To better investigate this, we develop AbGen-Eval, a meta-evaluation benchmark designed to assess the reliability of commonly used automated evaluation systems in measuring LLM performance on our task. We investigate various LLM-based evaluation methods on AbGen-Eval, providing insights for future research on developing more effective and reliable LLM-based evaluation systems for complex scientific tasks.

Peer review is fundamental to scientific research, but the growing volume of publications has intensified the challenges of this expertise-intensive process. While LLMs show promise in various scientific tasks, their potential to assist with peer review, particularly in identifying paper limitations, remains understudied. We first present a comprehensive taxonomy of limitation types in scientific research, with a focus on AI. Guided by this taxonomy, for studying limitations, we present LimitGen, the first comprehensive benchmark for evaluating LLMs’ capability to support early-stage feedback and complement human peer review. Our benchmark consists of two subsets: LimitGen-Syn, a synthetic dataset carefully created through controlled perturbations of high-quality papers, and LimitGen-Human, a collection of real human-written limitations. To improve the ability of LLM systems to identify limitations, we augment them with literature retrieval, which is essential for grounding identifying limitations in prior scientific findings. Our approach enhances the capabilities of LLM systems to generate limitations in research papers, enabling them to provide more concrete and constructive feedback.

There has been a surge of interest in harnessing the reasoning capabilities of Large Language Models (LLMs) to accelerate scientific discovery. While existing approaches rely on grounding the discovery process within the relevant literature, effectiveness varies significantly with the quality and nature of the retrieved literature. We address the challenge of retrieving prior work whose concepts can inspire solutions for a given research problem, a task we define as Methodology Inspiration Retrieval (MIR). We construct a novel dataset tailored for training and evaluating retrievers on MIR, and establish baselines. To address MIR, we build the Methodology Adjacency Graph (MAG); capturing methodological lineage through citation relationships. We leverage MAG to embed an “intuitive prior’’ into dense retrievers for identifying patterns of methodological inspiration beyond superficial semantic similarity. This achieves significant gains of +5.4 in Recall@3 and +7.8 in Mean Average Precision (mAP) over strong baselines. Further, we adapt LLM-based re-ranking strategies to MIR, yielding additional improvements of +4.5 in Recall@3 and +4.8 in mAP. Through extensive ablation studies and qualitative analyses, we exhibit the promise of MIR in enhancing automated scientific discovery and outline avenues for advancing inspiration-driven retrieval.

The rapid advancement in capabilities of large language models (LLMs) raises a pivotal question: How can LLMs accelerate scientific discovery? This work tackles the crucial first stage of research, generating novel hypotheses. While recent work on automated hypothesis generation focuses on multi-agent frameworks and extending test-time compute, none of the approaches effectively incorporate transparency and steerability through a synergistic Human-in-the-loop (HITL) approach. To address this gap, we introduce IRIS for interactive hypothesis generation, an open-source platform designed for researchers to leverage LLM-assisted scientific ideation. IRIS incorporates innovative features to enhance ideation, including adaptive test-time compute expansion via Monte Carlo Tree Search (MCTS), fine-grained feedback mechanism, and query-based literature synthesis. Designed to empower researchers with greater control and insight throughout the ideation process. We additionally conduct a user study with researchers across diverse disciplines, validating the effectiveness of our system in enhancing ideation. We open-source our code at https://github.com/Anikethh/IRIS-Interactive-Research-Ideation-System.

In the realm of research support tools, there exists a notable void in resources tailored specifically for aiding researchers during the crucial ideation phase of the research life-cycle. We address this gap by introducing ‘Acceleron’, a ‘Co-Pilot’ for researchers, designed specifically to accelerate the ideation phase of the research life-cycle. Leveraging the reasoning and domain-specific skills of Large Language Models (LLMs) within an agent-based architecture with distinct personas, Acceleron aids researchers through the formulation of a comprehensive research proposals. It emulates the ideation process, engaging researchers in an interactive fashion to validate the novelty of the proposal and generate plausible set-of hypotheses. Notably, it addresses challenges inherent in LLMs, such as hallucinations, implements a two-stage aspect-based retrieval to manage precision-recall trade-offs, and tackles issues of unanswerability. Our observations and end-user evaluations illustrate the efficacy of Acceleron as an enhancer of researcher’s productivity.

The inception of a research agenda typically commences with the creation of a comprehensive research proposal. The efficacy of the proposal often hinges on its ability to connect with the existing scientific literature that supports its ideas. To effectively assess the relevance of existing articles to a research proposal, it is imperative to categorize these articles into high-level thematic groups, referred to as topics, that align with the proposal. This paper introduces a novel task of aligning scientific articles, relevant to a proposal, with researcher-provided proposal topics. Additionally, we construct a dataset to serve as a benchmark for this task. We establish human and Large Language Model (LLM) baselines and propose a novel three-stage approach to address this challenge. We synthesize and use pseudo-labels that map proposal topics to text spans from cited articles to train Language Models (LMs) for two purposes: (i) as a retriever, to extract relevant text spans from cited articles for each topic, and (ii) as a classifier, to categorize the articles into the proposal topics. Our retriever-classifier pipeline, which employs very small open-source LMs fine-tuned with our constructed dataset, achieves results comparable to a vanilla paid LLM-based classifier, demonstrating its efficacy. However, a notable gap of 23.57 F1 score between our approach and the human baseline highlights the complexity of this task and emphasizes the need for further research.

When examining reviews of research papers, we can distinguish between two hypothetical referees: the maximally lenient referee who accepts any paper with a vacuous review and the maximally strict one who rejects any paper with an overly pedantic review. Clearly, both are of no practical value. Our interest is in a referee who makes a balanced judgement and provides a review abiding by the guidelines. In this paper, we present a case study of automatic correction of an existing machine-generated or human review. The AutoRef\ system implements an iterative approach that progressively “refines” a review by attempting to make it more compliant with pre-defined requirements of a “good” review. It implements the following steps: (1) Translate the review requirements into a specification in natural language, of “yes/no” questions; (2) Given a (paper,review) pair, extract answers to the questions; (3) Use the results in (2) to generate a new review; and (4) Return to Step (2) with the paper and the new review. Here, (2) and (3) are implemented by large language model (LLM) based agents. We present a case study using papers and reviews made available for the International Conference on Learning Representations (ICLR). Our initial empirical results suggest that AutoRef\ progressively improves the compliance of the generated reviews to the specification. Currently designed specification makes AutoRef\ progressively generate reviews which are stricter, making the decisions more inclined towards “rejections”. This demonstrates the applicability of $AutoRef $ for: (1) The progressive correction of overly lenient reviews, being useful for referees and meta-reviewers; and (2) The generation of progressively stricter reviews for a paper, starting from a vacuous review (“Great paper. Accept.”), facilitating authors when trying to assess weaknesses in their papers.

Answering complex reasoning questions from chart images is a challenging problem requiring a combination of natural language understanding, fine-grained perception, and analytical reasoning. Current chart-based Question Answering (QA) approaches largely address structural, visual or simple data retrieval-type questions with fixed-vocabulary answers and perform poorly on reasoning queries. We focus on answering realistic, complex, reasoning-based questions where the answer needs to be computed and not selected from a fixed set of choices. Our approach employs a neural semantic parser to transform Natural Language (NL) questions into SQL programs and execute them on a standardized schema populated from the extracted chart contents. In the absence of program annotations, i.e., in a weak supervision setting, we obtain initial SQL predictions from a pre-trained CodeT5 semantic parser and employ Filtered Iterative Back-Translation (FIBT) for iteratively augmenting our NL-SQL training set. The forward (neural semantic parser) and backward (language model) models are initially trained with an external NL-SQL dataset. We iteratively move towards the NL query distribution by generating NL questions from the synthesized SQL programs using a Probabilistic Context-Free Grammar (PCFG) where the production rule probabilities are induced to be inversely proportional to the probabilities in the training data. We filter out the generated NL queries with mismatched structures and compositions. Our FIBT approach achieves State-of-the-Art (SOTA) results on reasoning-based queries in the PlotQA dataset yielding a test accuracy of 60.44%, superseding the previous baselines by a large margin.

Cross-domain and cross-compositional generalization of Text-to-SQL semantic parsing is a challenging task. Existing Large Language Model (LLM) based solutions rely on inference-time retrieval of few-shot exemplars from the training set to synthesize a run-time prompt for each Natural Language (NL) test query. In contrast, we devise an algorithm which performs offline sampling of a minimal set-of few-shots from the training data, with complete coverage of SQL clauses, operators and functions, and maximal domain coverage within the allowed token length. This allows for synthesis of a fixed Generic Prompt (GP), with a diverse set-of exemplars common across NL test queries, avoiding expensive test time exemplar retrieval. We further auto-adapt the GP to the target database domain (DA-GP), to better handle cross-domain generalization; followed by a decomposed Least-To-Most-Prompting (LTMP-DA-GP) to handle cross-compositional generalization. The synthesis of LTMP-DA-GP is an offline task, to be performed one-time per new database with minimal human intervention. Our approach demonstrates superior performance on the KaggleDBQA dataset, designed to evaluate generalizability for the Text-to-SQL task. We further showcase consistent performance improvement of LTMP-DA-GP over GP, across LLMs and databases of KaggleDBQA, highlighting the efficacy and model agnostic benefits of our prompt based adapt and decompose approach.

Domain-specific Neural Machine Translation (NMT) model can provide improved performance, however, it is difficult to always access a domain-specific parallel corpus. Iterative Back-Translation can be used for fine-tuning an NMT model for a domain even if only a monolingual domain corpus is available. The quality of synthetic parallel corpora in terms of closeness to in-domain sentences can play an important role in the performance of the translation model. Recent works have shown that filtering at different stages of the back translation and weighting the sentences can provide state-of-the-art performance. In comparison, in this work, we observe that a simpler filtering approach based on a domain classifier, applied only to the pseudo-training data can consistently perform better, providing performance gains of 1.40, 1.82 and 0.76 in terms of BLEU score for Medical, Law and IT in one direction, and 1.28, 1.60 and 1.60 in the other direction in low resource scenario over competitive baselines. In the high resource scenario, our approach is at par with competitive baselines.

We consider the task of automatically classifying the persuasion strategy employed by an utterance in a dialog. We base our work on the PERSUASION-FOR-GOOD dataset, which is composed of conversations between crowdworkers trying to convince each other to make donations to a charity. Currently, the best known performance on this dataset, for classification of persuader’s strategy, is not derived by employing pretrained language models like BERT. We observe that a straightforward fine-tuning of BERT does not provide significant performance gain. Nevertheless, nonuniformly sampling to account for the class imbalance and a cost function enforcing a hierarchical probabilistic structure on the classes provides an absolute improvement of 10.79% F1 over the previously reported results. On the same dataset, we replicate the framework for classifying the persuadee’s response.

We consider a task based on CVPR 2018 challenge dataset on advertisement (Ad) understanding. The task involves detecting the viewer’s interpretation of an Ad image captured as text. Recent results have shown that the embedded scene-text in the image holds a vital cue for this task. Motivated by this, we fine-tune the base BERT model for a sentence-pair classification task. Despite utilizing the scene-text as the only source of visual information, we could achieve a hit-or-miss accuracy of 84.95% on the challenge test data. To enable BERT to process other visual information, we append image captions to the scene-text. This achieves an accuracy of 89.69%, which is an improvement of 4.7%. This is the best reported result for this task.

Document-Level Machine Translation (MT) has become an active research area among the NLP community in recent years. Unlike sentence-level MT, which translates the sentences independently, document-level MT aims to utilize contextual information while translating a given source sentence. This paper demonstrates our submission (Team ID - DEEPNLP) to the Document-Level Translation task organized by WAT 2020. This task focuses on translating texts from a business dialog corpus while optionally utilizing the context present in the dialog. In our proposed approach, we utilize publicly available parallel corpus from different domains to train an open domain base NMT model. We then use monolingual target data to create filtered pseudo parallel data and employ Back-Translation to fine-tune the base model. This is further followed by fine-tuning on the domain-specific corpus. We also ensemble various models to improvise the translation performance. Our best models achieve a BLEU score of 26.59 and 22.83 in an unconstrained setting and 15.10 and 10.91 in the constrained settings for En->Ja & Ja->En direction, respectively.

Recent research on cross-lingual transfer show state-of-the-art results on benchmark datasets using pre-trained language representation models (PLRM) like BERT. These results are achieved with the traditional training approaches, such as Zero-shot with no data, Translate-train or Translate-test with machine translated data. In this work, we propose an approach of “Multilingual Co-training” (MCT) where we augment the expert annotated dataset in the source language (English) with the corresponding machine translations in the target languages (e.g. Arabic, Spanish) and fine-tune the PLRM jointly. We observe that the proposed approach provides consistent gains in the performance of BERT for multiple benchmark datasets (e.g. 1.0% gain on MLDocs, and 1.2% gain on XNLI over translate-train with BERT), while requiring a single model for multiple languages. We further consider a FAQ dataset where the available English test dataset is translated by experts into Arabic and Spanish. On such a dataset, we observe an average gain of 4.9% over all other cross-lingual transfer protocols with BERT. We further observe that domain-specific joint pre-training of the PLRM using HR policy documents in English along with the machine translations in the target languages, followed by the joint finetuning, provides a further improvement of 2.8% in average accuracy.