DA-Code: Agent Data Science Code Generation Benchmark for Large Language Models

We introduce DA-Code, a code generation benchmark specifically designed to assess LLMs on agent-based data science tasks. This benchmark features three core elements: First, the tasks within DA-Code are inherently challenging, setting them apart from traditional code generation tasks and demanding advanced coding skills in grounding and planning. Second, examples in DA-Code are all based on real and diverse data, covering a wide range of complex data wrangling and analytics tasks. Third, to solve the tasks, the models must utilize complex data science programming languages, to perform intricate data processing and derive the answers. We set up the benchmark in a controllable and executable environment that aligns with real-world data analysis scenarios and is scalable. The annotators meticulously design the evaluation suite to ensure the accuracy and robustness of the evaluation. We develop the DA-Agent baseline. Experiments show that although the baseline performs better than other existing frameworks, using the current best LLMs achieves only 30.5% accuracy, leaving ample room for improvement. We release our benchmark at [https://da-code-bench.github.io](https://da-code-bench.github.io).

Beyond Instruction Following: Evaluating Rule Following of Large Language Models

Although Large Language Models (LLMs) have demonstrated strong instruction-following ability to be helpful, they are further supposed to be controlled and guided by rules in real-world scenarios to be safe, and accurate in responses. This demands the possession of rule-following capability of LLMs. However, few works have made a clear evaluation of the rule-following capability of LLMs. Previous studies that try to evaluate the rule-following capability of LLMs fail to distinguish the rule-following scenarios from the instruction-following scenarios. Therefore, this paper first makes a clarification of the concept of rule-following, and curates a comprehensive benchmark, RuleBench, to evaluate a diversified range of rule-following abilities. Our experimental results on a variety of LLMs show that they are still limited in following rules. Our further analysis provides insights into the improvements for LLMs toward a better rule-following intelligent agent. The data and code can be found at: https://anonymous.4open.science/r/llm-rule-following-B3E3/

Multilingual Knowledge Graph Completion from Pretrained Language Models with Knowledge Constraints

Multilingual Knowledge Graph Completion (mKGC) aim at solving queries like (h, r, ?) in different languages by reasoning a tail entity t thus improving multilingual knowledge graphs. Previous studies leverage multilingual pretrained language models (PLMs) and the generative paradigm to achieve mKGC. Although multilingual pretrained language models contain extensive knowledge of different languages, its pretraining tasks cannot be directly aligned with the mKGC tasks. Moreover, the majority of KGs and PLMs currently available exhibit a pronounced English-centric bias. This makes it difficult for mKGC to achieve good results, particularly in the context of low-resource languages. To overcome previous problems, this paper introduces global and local knowledge constraints for mKGC. The former is used to constrain the reasoning of answer entities, while the latter is used to enhance the representation of query contexts. The proposed method makes the pretrained model better adapt to the mKGC task. Experimental results on public datasets demonstrate that our method outperforms the previous SOTA on Hits@1 and Hits@10 by an average of 12.32% and 16.03%, which indicates that our proposed method has significant enhancement on mKGC.

Find Parent then Label Children: A Two-stage Taxonomy Completion Method with Pre-trained Language Model

Taxonomies, which organize domain concepts into hierarchical structures, are crucial for building knowledge systems and downstream applications. As domain knowledge evolves, taxonomies need to be continuously updated to include new concepts. Previous approaches have mainly focused on adding concepts to the leaf nodes of the existing hierarchical tree, which does not fully utilize the taxonomy's knowledge and is unable to update the original taxonomy structure (usually involving non-leaf nodes). In this paper, we propose a two-stage method called ATTEMPT for taxonomy completion. Our method inserts new concepts into the correct position by finding a parent node and labeling child nodes. Specifically, by combining local nodes with prompts to generate natural sentences, we take advantage of pre-trained language models for hypernym/hyponymy recognition. Experimental results on two public datasets (including six domains) show that ATTEMPT performs best on both taxonomy completion and extension tasks, surpassing existing methods.

From Instance Training to Instruction Learning: Task Adapters Generation from Instructions

Large language models (LLMs) have acquired the ability to solve general tasks by utilizing instruction finetuning (IFT). However, IFT still relies heavily on instance training of extensive task data, which greatly limits the adaptability of LLMs to real-world scenarios where labeled task instances are scarce and broader task generalization becomes paramount. Contrary to LLMs, humans acquire skills and complete tasks not merely through repeated practice but also by understanding and following instructional guidelines. This paper is dedicated to simulating human learning to address the shortcomings of instance training, focusing on instruction learning to enhance cross-task generalization. Within this context, we introduce Task Adapters Generation from Instructions (TAGI), which automatically constructs the task-specific model in a parameter generation manner based on the given task instructions without retraining for unseen tasks. Specifically, we utilize knowledge distillation to enhance the consistency between TAGI developed through Learning with Instruction and task-specific models developed through Training with Instance, by aligning the labels, output logits, and adapter parameters between them. TAGI is endowed with cross-task generalization capabilities through a two-stage training process that includes hypernetwork pretraining and finetuning. We evaluate TAGI on the Super-Natural Instructions and P3 datasets. The experimental results demonstrate that TAGI can match or even outperform traditional meta-trained models and other hypernetwork models, while significantly reducing computational requirements.

Generate-on-Graph: Treat LLM as both Agent and KG in Incomplete Knowledge Graph Question Answering

To address the issue of insufficient knowledge and the tendency to generate hallucination in Large Language Models (LLMs), numerous studies have endeavored to integrate LLMs with Knowledge Graphs (KGs). However, all these methods are evaluated on conventional Knowledge Graph Question Answering (KGQA) with complete KGs, where the factual triples involved in each question are entirely covered by the given KG. In this situation, LLM mainly acts as an agent to find answer entities by exploring the KG, rather than effectively integrating internal and external knowledge sources. However, in real-world scenarios, KGs are often incomplete to cover all the knowledge required to answer questions. To simulate real-world scenarios and evaluate the ability of LLMs to integrate internal and external knowledge, in this paper, we propose leveraging LLMs for QA under Incomplete Knowledge Graph (IKGQA), where the given KG doesn't include all the factual triples involved in each question. To handle IKGQA, we propose a training-free method called Generate-on-Graph (GoG) that can generate new factual triples while exploring on KGs. Specifically, we propose a selecting-generating-answering framework, which not only treat the LLM as an agent to explore on KGs, but also treat it as a KG to generate new facts based on the explored subgraph and its inherent knowledge. Experimental results on two datasets demonstrate that our GoG can solve IKGQA to a certain extent, while almost all previous methods cannot perform well on IKGQA.

Imagination Augmented Generation: Learning to Imagine Richer Context for Question Answering over Large Language Models

Retrieval-Augmented-Generation and Gener-ation-Augmented-Generation have been proposed to enhance the knowledge required for question answering over Large Language Models (LLMs). However, the former depends on external resources, and both require incorporating the explicit documents into the context, which results in longer contexts that lead to more resource consumption. Recent works indicate that LLMs have modeled rich knowledge, albeit not effectively triggered or activated. Inspired by this, we propose a novel knowledge-augmented framework, Imagination-Augmented-Generation (IAG), which simulates the human capacity to compensate for knowledge deficits while answering questions solely through imagination, without relying on external resources. Guided by IAG, we propose an imagine richer context method for question answering (IMcQA), which obtains richer context through the following two modules: explicit imagination by generating a short dummy document with long context compress and implicit imagination with HyperNetwork for generating adapter weights. Experimental results on three datasets demonstrate that IMcQA exhibits significant advantages in both open-domain and closed-book settings, as well as in both in-distribution performance and out-of-distribution generalizations. Our code will be available at https://github.com/Xnhyacinth/IAG.

BP4ER: Bootstrap Prompting for Explicit Reasoning in Medical Dialogue Generation

Medical dialogue generation (MDG) has gained increasing attention due to its substantial practical value. Previous works typically employ a sequence-to-sequence framework to generate medical responses by modeling dialogue context as sequential text with annotated medical entities. While these methods have been successful in generating fluent responses, they fail to provide process explanations of reasoning and require extensive entity annotation. To address these limitations, we propose the method Bootstrap Prompting for Explicit Reasoning in MDG (BP4ER), which explicitly model MDG's multi-step reasoning process and iteratively enhance this reasoning process. We employ a least-to-most prompting strategy to guide a large language model (LLM) in explicit reasoning, breaking down MDG into simpler sub-questions. These sub-questions build on answers from previous ones. Additionally, we also introduce two distinct bootstrapping techniques for prompting, which autonomously correct errors and facilitate the LLM's explicit reasoning. This approach eliminates the need for entity annotation and increases the transparency of the MDG process by explicitly generating the intermediate reasoning chain. The experimental findings on the two public datasets indicate that BP4ER outperforms state-of-the-art methods in terms of both objective and subjective evaluation metrics.

ItD: Large Language Models Can Teach Themselves Induction through Deduction

Although Large Language Models (LLMs) are showing impressive performance on a wide range of Natural Language Processing tasks, researchers have found that they still have limited ability to conduct induction. Recent works mainly adopt ``post processes'' paradigms to improve the performance of LLMs on induction (e.g., the hypothesis search & refinement methods), but their performance is still constrained by the inherent inductive capability of the LLMs. In this paper, we propose a novel framework, Induction through Deduction (ItD), to enable the LLMs to teach themselves induction through deduction. The ItD framework is composed of two main components: a Deductive Data Generation module to generate induction data and a Naive Bayesian Induction module to optimize the fine-tuning and decoding of LLMs. Our empirical results showcase the effectiveness of ItD on two induction benchmarks, achieving relative performance improvement of 36% and 10% compared with previous state-of-the-art, respectively. Our ablation study verifies the effectiveness of two key modules of ItD. We also verify the effectiveness of ItD across different LLMs and deductors. The data and code of this paper can be found at https://anonymous.4open.science/r/ItD-E844.

From Chain to Tree: Refining Chain-like Rules into Tree-like Rules on Knowledge Graphs

With good explanatory power and controllability, rule-based methods play an important role in many tasks such as knowledge reasoning and decision support. However, existing studies primarily focused on learning chain-like rules, which limit their semantic expressions and accurate prediction abilities. As a result, chain-like rules usually fire on the incorrect grounding values, producing inaccurate or even erroneous reasoning results. In this paper, we propose the concept of tree-like rules on knowledge graphs to expand the application scope and improve the reasoning ability of rule-based methods. Meanwhile, we propose an effective framework for refining chain-like rules into tree-like rules. Experimental comparisons on four public datasets show that the proposed framework can easily adapt to other chain-like rule induction methods and the refined tree-like rules consistently achieve better performances than chain-like rules on link prediction. The data and code of this paper can be available at https://anonymous.4open.science/r/tree-rule-E3CD/.