Tian Lan, Yiqian Yang, Qianghuai Jia, Li Zhu, Hui Jiang, Hang Zhu, Weihua Luo, Longyue Wang. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2026.

Large Language Models (LLMs) have made significant strides in Natural Language Processing and coding, yet they struggle with robustness and accuracy in complex function calls. To tackle these challenges, this paper introduces ADC, an innovative approach that enhances LLMs’ ability to follow function formats and match complex parameters. ADC utilizes a high-quality code fine-tuning dataset with line-level execution feedback, providing granular process supervision that fosters strong logical reasoning and adherence to function formats. It also employs an adversarial dataset generation process to improve parameter matching. The staged training methodology capitalizes on both enriched code datasets and refined adversarial datasets, leading to marked improvements in function calling capabilities on the Berkeley Function-Calling Leaderboard (BFCL) Benchmark. The innovation of ADC lies in its strategic combination of process supervision, adversarial refinement, and incremental learning, setting a new standard for LLM proficiency in complex function calling.

Shuofei Qiao, Honghao Gui, Chengfei Lv, Qianghuai Jia, Huajun Chen, Ningyu Zhang. Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers). 2024.

Conceptual graphs, which is a particular type of Knowledge Graphs, play an essential role in semantic search. Prior conceptual graph construction approaches typically extract high-frequent, coarse-grained, and time-invariant concepts from formal texts such as Wikipedia. In real applications, however, it is necessary to extract less-frequent, fine-grained, and time-varying conceptual knowledge and build taxonomy in an evolving manner. In this paper, we introduce an approach to implementing and deploying the conceptual graph at Alibaba. Specifically, We propose a framework called AliCG which is capable of a) extracting fine-grained concepts by a novel bootstrapping with alignment consensus approach, b) mining long-tail concepts with a novel low-resource phrase mining approach, c) updating the graph dynamically via a concept distribution estimation method based on implicit and explicit user behaviors. We have deployed the conceptual graph at Alibaba UC Browser. Extensive offline evaluation as well as online A/B testing demonstrate the efficacy of our approach.

Current image search engines suffer from a radical variance in retrieval performance over different queries. It is therefore desirable to identify those “difficult” queries in order to handle them properly. Query difficulty estimation is an attempt to predict the performance of the search results returned by an image search system. Most existing methods for query difficulty estimation focus on investigating statistical characteristics of the returned images only, while neglecting very important information , i.e., the query and its relationship with returned images. This relationship plays a crucial role in query difficulty estimation and should be explored further. In this paper we propose a novel query difficulty estimation method with query reconstruction error. This method is proposed based on the observation that, given the images returned for an unknown query, we can easily deduce what the query is from those images if the search results are high quality (i.e., lots of relevant images returned); otherwise, it is difficult to deduce the original query. Therefore, we propose to predict the query difficulty by measuring to what extent the original query can be recovered from the image search results. Specifically, we first reconstruct a visual query from the returned images to summarize their visual theme, and then use the reconstruction error, i.e., the distance between the original textual query and the reconstructed visual query, to estimate the query difficulty. We conduct extensive experiments on two real-world Web image datasets and demonstrate the effectiveness of the proposed method.

Query difficulty estimation (QDE) attempts to automatically predict the performance of the search results returned for a given query. QDE has been widely investigated in text document retrieval for many years. However, few research works have been explored in image retrieval. State-of-the-art QDE methods in image retrieval mainly investigate the statistical characteristics (coherence, robustness, etc.) of the returned images to derive a value for indicating the query difficulty degree. To the best of our knowledge, little research has been done to directly estimate the real retrieval performance of the search results, such as average precision, instead of only an indicator. In this paper, we propose a novel query difficulty estimation approach which automatically estimate the average precision of the image search results. Specifically, we first select a set of query relevant and query irrelevant images for each query via pseudo relevance feedback. Then an efficient and effective voting scheme is proposed to estimate the relevance label of each image in the search results. Based on the images' relevance labels, the average precision of the search results returned for the given query is derived. The experimental results on a benchmark image search dataset demonstrate the effectiveness of the proposed method.