While large language models (LLMs) perform well on table tasks, they still make data referencing errors (DREs), i.e., incorrectly citing or omitting table values, despite understanding the table structure. Beyond final-answer accuracy, DREs directly compromise the correctness and reliability of intermediate reasoning steps. Yet prior studies have only offered limited, small-scale analyses. In this work, we present the first systematic evaluation of tabular data referencing errors across different models and tasks. Our results show that DREs occur across all tested models (1.7B to 20B parameters). Furthermore, we demonstrate that incorporating data referencing as a critic significantly improves answer accuracy up to 12.0%, through critic-based filtering and rejection sampling. Finally, we trained a lightweight 4B-parameter critic model that achieves an average F1 score of 78.2% in detecting both in-distribution and out-of-distribution DREs, and effectively assists inference for larger models.

While large language models (LLMs) have substantially improved Text-to-SQL generation, a pronounced gap remains between AI systems and human experts on challenging benchmarks such as BIRD-SQL. We argue this gap stems largely from the prevailing single-pass paradigm, which lacks the iterative reasoning, schema exploration, and error-correction behaviors that humans naturally employ. To address this limitation, we introduce SQL-Trail, a multi-turn reinforcement learning (RL) agentic framework for Text-to-SQL. Rather than producing a query in one shot, SQL-Trail interacts with the database environment and uses execution feedback to iteratively refine its predictions. Our approach centers on two key ideas: (i) an adaptive turn-budget allocation mechanism that scales the agent’s interaction depth to match question difficulty, and (ii) a composite reward panel that jointly incentivizes SQL correctness and efficient exploration. Across benchmarks, SQL-Trail sets a new state of the art and delivers strong data efficiency—up to **18×** higher than prior single-pass RL state-of-the-art methods. Notably, our 7B and 14B models outperform substantially larger proprietary systems by **5%** on average, underscoring the effectiveness of interactive, agentic workflows for robust Text-to-SQL generation.

Given a query table, how can we effectively discover multi-key joinable tables on the web? This can be seen as a retrieval task, where users can lookup on the web for tables related to an existing one. Searching and discovering such joinable tables is critical to data analysts and data scientists for reporting, establishing correlations and training machine learning models. Existing joinable table search methods have mostly focused on single key (unary) joins, where a single column is the join key. However, these methods are ineffective when dealing with join keys composed of multiple columns (n-ary joins), which are prevalent on web table corpora. In this paper, we introduce PolyJoin, which finds multi-key semantically-joinable tables on the web, given a query table. PolyJoin employs a multi-key encoder and a novel self-supervised training method to generate the representations of multiple join keys, preserving the alignment across multiple columns. In particular, PolyJoin is equipped with a hierarchical contrastive learning technique to further enhance the model’s semantic understanding of multi-key joinable tables. PolyJoin outperforms the state-of-the-art methods by 2.89% and 3.67% with respect to MAP@30 and R@30 on two real-world web table benchmarks, respectively.

Natural language understanding over tabular data has played a significant role in data discovery tasks such as joinable and unionable table search. State-of-the-art approaches adopt large language models (LLMs) pre-trained over massive text corpora to learn and evaluate the table semantic relatedness. Existing methods typically follow a pretrain-and-finetune paradigm, namely fine-tuning an LLM using tabular data with table relatedness labels. To enhance model’s understanding of tabular data, recent studies include auxiliary tasks such as entity resolution and column type classification in the fine-tuning phase. In spite of achieving performance gain from these supervisions, there is a lack of study on how these supervisions complement or even contrast each other, leading to a subpar performance on the final data discovery tasks. In this paper, we propose a simple yet effective multi-task fine-tuning framework named DiscoverGPT that holistically discovers and leverages the intricate relationships among the supervisions to optimize the performance on the data discovery task. Moreover, DiscoverGPT is plug-and-play that allows a broad range of open-domain auxiliary tasks to be incorporated, by utilizing the generative power of LLMs. We demonstrate the usability and effectiveness of DiscoverGPT with baseline comparisons and ablation studies. DiscoverGPT outperforms the best performing baseline by up to 7% in F1 score.

Knowledge graph question answering (KGQA) presents significant challenges due to the structural and semantic variations across input graphs. Existing works rely on Large Language Model (LLM) agents for graph traversal and retrieval; an approach that is sensitive to traversal initialization, as it is prone to entity linking errors and may not generalize well to custom (“bring-your-own”) KGs. We introduce BYOKG-RAG, a framework that enhances KGQA by synergistically combining LLMs with specialized graph retrieval tools. In BYOKG-RAG, LLMs generate critical graph artifacts (question entities, candidate answers, reasoning paths, and OpenCypher queries), and graph tools link these artifacts to the KG and retrieve relevant graph context. The retrieved context enables the LLM to iteratively refine its graph linking and retrieval, before final answer generation. By retrieving context from different graph tools, BYOKG-RAG offers a more general and robust solution for QA over custom KGs. Through experiments on five benchmarks spanning diverse KG types, we demonstrate that BYOKG-RAG outperforms the second-best graph retrieval method by 4.5% points while showing better generalization to custom KGs. BYOKG-RAG framework is open-sourced at https://github.com/awslabs/graphrag-toolkit.

Given a semi-structured knowledge base (SKB), where text documents are interconnected by relations, how can we effectively retrieve relevant information to answer user questions?Retrieval-Augmented Generation (RAG) retrieves documents to assist large language models (LLMs) in question answering; while Graph RAG (GRAG) uses structured knowledge bases as its knowledge source.However, many questions require both textual and relational information from SKB — referred to as “hybrid” questions — which complicates the retrieval process and underscores the need for a hybrid retrieval method that leverages both information.In this paper, through our empirical analysis, we identify key insights that show why existing methods may struggle with hybrid question answering (HQA) over SKB. Based on these insights, we propose HybGRAG for HQA, consisting of a retriever bank and a critic module, with the following advantages:1. Agentic, it automatically refines the output by incorporating feedback from the critic module, 2. Adaptive, it solves hybrid questions requiring both textual and relational information with the retriever bank,3. Interpretable, it justifies decision making with intuitive refinement path, and4. Effective, it surpasses all baselines on HQA benchmarks.In experiments on the STaRK benchmark, HybGRAG achieves significant performance gains, with an average relative improvement in Hit@1 of 51%.

In-context learning (ICL) adapts Large Language Models (LLMs) to new tasks, without requiring any parameter updates, but few annotated examples as input. In this work, we investigate selective annotation for ICL, where there is a limited budget for annotating examples, similar to low-budget active learning (AL). Although uncertainty-based selection is unreliable with few annotated data, we present CoverICL, an adaptive graph-based selection algorithm, that effectively incorporates uncertainty sampling into selective annotation for ICL. First, CoverICL builds a nearest-neighbor graph based on the semantic similarity between candidate ICL examples. Then, CoverICL employs uncertainty estimation by the LLM to identify hard examples for the task. Selective annotation is performed over the active graph of the hard examples, adapting the process to the particular LLM used and the task tackled. CoverICL selects the most representative examples by solving a Maximum Coverage problem, approximating diversity-based sampling. Extensive experiments on ten datasets and seven LLMs show that, by incorporating uncertainty via coverage on the active graph, CoverICL (1) outperforms existing AL methods for ICL by 2–4.6% accuracy points, (2) is up to 2x more budget-efficient than SOTA methods for low-budget AL, and (3) generalizes better across tasks compared to non-graph alternatives.

Recent advances in large language models have revolutionized many sectors, including the database industry. One common challenge when dealing with large volumes of tabular data is the pervasive use of abbreviated column names, which can negatively impact performance on various data search, access, and understanding tasks. To address this issue, we introduce a new task, called NameGuess, to expand column names (used in database schema) as a natural language generation problem. We create a training dataset of 384K abbreviated-expanded column pairs using a new data fabrication method and a human-annotated evaluation benchmark that includes 9.2K examples from real-world tables. To tackle the complexities associated with polysemy and ambiguity in NameGuess, we enhance auto-regressive language models by conditioning on table content and column header names – yielding a fine-tuned model (with 2.7B parameters) that matches human performance. Furthermore, we conduct a comprehensive analysis (on multiple LLMs) to validate the effectiveness of table content in NameGuess and identify promising future opportunities. Code has been made available at https://github.com/amazon-science/nameguess.

The success of sites such as ACLED and Our World in Data have demonstrated the massive utility of extracting events in structured formats from large volumes of textual data in the formof news, social media, blogs and discussion forums. Event extraction can provide a window into ongoing geopolitical crises and yield actionable intelligence. In this work, we cast socio-political event extraction as a machine reading comprehension (MRC) task. % With the proliferation of large pretrained language models Machine Reading Comprehension (MRC) has emerged as a new paradigm for event extraction in recent times. In this approach, extraction of social-political actors and targets from a sentence is framed as an extractive question-answering problem conditioned on an event type. There are several advantages of using MRC for this task including the ability to leverage large pretrained multilingual language models and their ability to perform zero-shot extraction. Moreover, we find that the problem of long-range dependencies, i.e., large lexical distance between trigger and argument words and the difficulty of processing syntactically complex sentences plague MRC-based approaches. To address this, we present a general approach to improve the performance of MRC-based event extraction by performing unsupervised sentence simplification guided by the MRC model itself. We evaluate our approach on the ICEWS geopolitical event extraction dataset, with specific attention to ‘Actor’ and ‘Target’ argument roles. We show how such context simplification can improve the performance of MRC-based event extraction by more than 5% for actor extraction and more than 10% for target extraction.

Predicting user intent and detecting the corresponding slots from text are two key problems in Natural Language Understanding (NLU). Since annotated datasets are only available for a handful of languages, our work focuses particularly on a zero-shot scenario where the target language is unseen during training. In the context of zero-shot learning, this task is typically approached using representations from pre-trained multilingual language models such as mBERT or by fine-tuning on data automatically translated into the target language. We propose a novel method which augments monolingual source data using multilingual code-switching via random translations, to enhance generalizability of large multilingual language models when fine-tuning them for downstream tasks. Experiments on the MultiATIS++ benchmark show that our method leads to an average improvement of +4.2% in accuracy for the intent task and +1.8% in F1 for the slot-filling task over the state-of-the-art across 8 typologically diverse languages. We also study the impact of code-switching into different families of languages on downstream performance. Furthermore, we present an application of our method for crisis informatics using a new human-annotated tweet dataset of slot filling in English and Haitian Creole, collected during the Haiti earthquake.