Modern code agents achieve strong results on challenging software engineering benchmarks such as SWE-bench, but solving each issue remains expensive: most inference cost is spent not on patch generation, but on repository exploration and search, accounting for up to 56% of tokens in our experiments. We propose SAGE, a modular approach that trains a small searcher model to handle codebase exploration as a tool for a frozen large solver model. We first distill the search trajectories from a strong agent to obtain a compact searcher with comparable retrieval quality. We then apply reinforcement learning to optimize the searcher for usefulness under the solver's fixed interface, using step-level feedback that directly evaluates whether retrieved context is actionable for downstream patching. On SWE-bench Verified, SAGE improves resolve rate while reducing search overhead by 67% and overall cost by 21%, demonstrating a practical path to cheaper, modular software engineering agents.

Retrieval-augmented code generation commonly conditions a decoder on large retrieved snippets, which couples online cost to repository size and introduces long-context noise. We present Hierarchical Embedding Fusion (HEF), a two-stage repository representation for code completion: (i) an offline cache that compresses repository chunks into a reusable hierarchy of dense vectors using a small fuser model, and (ii) an online interface that maps a small number of retrieved vectors into learned pseudo-tokens consumed by a code generator. This replaces thousands of retrieved tokens with a fixed pseudo-token budget while retaining access to repository-level information.

We introduce ReplaceMe, a generalized training-free depth pruning method that effectively replaces transformer blocks with a linear operation, while maintaining high performance for low compression ratios. In contrast to conventional pruning approaches that require additional training or fine-tuning, our approach requires only a small calibration dataset that is used to estimate a linear transformation, which approximates the pruned blocks. The estimated linear mapping can be seam- lessly merged with the remaining transformer blocks, eliminating the need for any additional network parameters. Our experiments show that ReplaceMe consistently outperforms other training-free approaches and remains highly competitive with state-of-the-art pruning methods that involve extensive retraining/fine-tuning and architectural modifications. Applied to several large language models (LLMs), ReplaceMe achieves up to 25% pruning while retaining approximately 90% of the original model’s performance on open benchmarks—without any training or healing steps, resulting in minimal computational overhead. We provide an open- source library implementing ReplaceMe alongside several state-of-the-art depth pruning techniques, available at https://github.com/mts-ai/ReplaceMe.

Code search is an important and well-studied task, but it usually means searching for code by a text query. We argue that using a code snippet (and possibly an error traceback) as a query while looking for bugfixing instructions and code samples is a natural use case not covered by prior art. Moreover, existing datasets use code comments rather than full-text descriptions as text, making them unsuitable for this use case. We present a new SearchBySnippet dataset implementing the search-by-code use case based on StackOverflow data; we show that on SearchBySnippet, existing architectures fall short of a simple BM25 baseline even after fine-tuning. We present a new single encoder model SnippeR that outperforms several strong baselines on SearchBySnippet with a result of 0.451 Recall@10; we propose the SearchBySnippet dataset and SnippeR as a new important benchmark for code search evaluation.

Data collection and mining is a crucial bottleneck for cross-lingual information retrieval (CLIR). While previous works used machine translation and iterative training, we present a novel approach to cross-lingual pretraining called LAPCA (language-agnostic pretraining with cross-lingual alignment). We train the LAPCA-LM model based on XLM-RoBERTa and łexa that significantly improves cross-lingual knowledge transfer for question answering and sentence retrieval on, e.g., XOR-TyDi and Mr. TyDi datasets, and in the zero-shot cross-lingual scenario performs on par with supervised methods, outperforming many of them on MKQA.

Abstract Recent research has reported that standard fine-tuning approaches can be unstable due to being prone to various sources of randomness, including but not limited to weight initialization, training data order, and hardware. Such brittleness can lead to different evaluation results, prediction confidences, and generalization inconsistency of the same models independently fine-tuned under the same experimental setup. Our paper explores this problem in natural language inference, a common task in benchmarking practices, and extends the ongoing research to the multilingual setting. We propose six novel textual entailment and broad-coverage diagnostic datasets for French, German, and Swedish. Our key findings are that the mBERT model demonstrates fine-tuning instability for categories that involve lexical semantics, logic, and predicate-argument structure and struggles to learn monotonicity, negation, numeracy, and symmetry. We also observe that using extra training data only in English can enhance the generalization performance and fine-tuning stability, which we attribute to the cross-lingual transfer capabilities. However, the ratio of particular features in the additional training data might rather hurt the performance for model instances. We are publicly releasing the datasets, hoping to foster the diagnostic investigation of language models (LMs) in a cross-lingual scenario, particularly in terms of benchmarking, which might promote a more holistic understanding of multilingualism in LMs and cross-lingual knowledge transfer.

State of the art neural methods for open information extraction (OpenIE) usually extract triplets (or tuples) iteratively in an autoregressive or predicate-based manner in order not to produce duplicates. In this work, we propose a different approach to the problem that can be equally or more successful. Namely, we present a novel single-pass method for OpenIE inspired by object detection algorithms from computer vision. We use an order-agnostic loss based on bipartite matching that forces unique predictions and a Transformer-based encoder-only architecture for sequence labeling. The proposed approach is faster and shows superior or similar performance in comparison with state of the art models on standard benchmarks in terms of both quality metrics and inference time. Our model sets the new state of the art performance of 67.7% F1 on CaRB evaluated as OIE2016 while being 3.35x faster at inference than previous state of the art. We also evaluate the multilingual version of our model in the zero-shot setting for two languages and introduce a strategy for generating synthetic multilingual data to fine-tune the model for each specific language. In this setting, we show performance improvement of 15% on multilingual Re-OIE2016, reaching 75% F1 for both Portuguese and Spanish languages. Code and models are available at https://github.com/sberbank-ai/DetIE.

Nikita Sorokin, Dmitry Abulkhanov, Irina Piontkovskaya, Valentin Malykh. Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. 2022.

Sub-tasks of intent classification, such as robustness to distribution shift, adaptation to specific user groups and personalization, out-ofdomain detection, require extensive and flexible datasets for experiments and evaluation.As collecting such datasets is time-and laborconsuming, we propose to use text generation methods to gather datasets.The generator should be trained to generate utterances that belong to the given intent.We explore two approaches to generating task-oriented utterances.In the zero-shot approach, the model is trained to generate utterances from seen intents and is further used to generate utterances for intents unseen during training.In the oneshot approach, the model is presented with a single utterance from a test intent.We perform a thorough automatic, and human evaluation of the dataset generated utilizing two proposed approaches.Our results reveal that the attributes of the generated data are close to original test sets, collected via crowd-sourcing.

MOTIVATION: Drugs and diseases play a central role in many areas of biomedical research and healthcare. Aggregating knowledge about these entities across a broader range of domains and languages is critical for information extraction (IE) applications. To facilitate text mining methods for analysis and comparison of patient's health conditions and adverse drug reactions reported on the Internet with traditional sources such as drug labels, we present a new corpus of Russian language health reviews. RESULTS: The Russian Drug Reaction Corpus (RuDReC) is a new partially annotated corpus of consumer reviews in Russian about pharmaceutical products for the detection of health-related named entities and the effectiveness of pharmaceutical products. The corpus itself consists of two parts, the raw one and the labeled one. The raw part includes 1.4 million health-related user-generated texts collected from various Internet sources, including social media. The labeled part contains 500 consumer reviews about drug therapy with drug- and disease-related information. Labels for sentences include health-related issues or their absence. The sentences with one are additionally labeled at the expression level for identification of fine-grained subtypes such as drug classes and drug forms, drug indications and drug reactions. Further, we present a baseline model for named entity recognition (NER) and multilabel sentence classification tasks on this corpus. The macro F1 score of 74.85% in the NER task was achieved by our RuDR-BERT model. For the sentence classification task, our model achieves the macro F1 score of 68.82% gaining 7.47% over the score of BERT model trained on Russian data. AVAILABILITY AND IMPLEMENTATION: We make the RuDReC corpus and pretrained weights of domain-specific BERT models freely available at https://github.com/cimm-kzn/RuDReC. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

The existing dialogue summarization corpora are significantly extractive.We introduce a methodology for dataset extractiveness evaluation and present a new low-extractive corpus of movie dialogues for abstractive text summarization along with baseline evaluation.The corpus contains 153k dialogues and consists of three parts: 1) automatically aligned subtitles, 2) automatically aligned scenes from scripts, and 3) manually aligned scenes from scripts.We also present an alignment algorithm which we use to construct the corpus. 1

Tatiana Shavrina, Alena Fenogenova, Emelyanov Anton, Denis Shevelev, Ekaterina Artemova, Valentin Malykh, Vladislav Mikhailov, Maria Tikhonova, Andrey Chertok, Andrey Evlampiev. Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP). 2020.

Artificial General Intelligence (AGI) is showing growing performance in numerous applications - beating human performance in Chess and Go, using knowledge bases and text sources to answer questions (SQuAD) and even pass human examination (Aristo project). In this paper, we describe the results of AI Journey, a competition of AI-systems aimed to improve AI performance on knowledge bases, reasoning and text generation. Competing systems pass the final native language exam (in Russian), including versatile grammar tasks (test and open questions) and an essay, achieving a high score of 69%, with 68% being an average human result. During the competition, a baseline for the task and essay parts was proposed, and 80+ systems were submitted, showing different approaches to task understanding and reasoning. All the data and solutions can be found on github https://github.com/sberbank-ai/combined_solution_aij2019

Recent research has shown the advantages of using autoencoders based on deep neural networks for collaborative filtering. In particular, the recently proposed Mult-VAE model, which used the multinomial likelihood variational autoencoders, has shown excellent results for top-N recommendations. In this work, we propose the Recommender VAE (RecVAE) model that originates from our research on regularization techniques for variational autoencoders. RecVAE introduces several novel ideas to improve Mult-VAE, including a novel composite prior distribution for the latent codes, a new approach to setting the beta hyperparameter for the beta-VAE framework, and a new approach to training based on alternating updates. In experimental evaluation, we show that RecVAE significantly outperforms previously proposed autoencoder-based models, including Mult-VAE and RaCT, across classical collaborative filtering datasets, and present a detailed ablation study to assess our new developments. Code and models are available at https://github.com/ilya-shenbin/RecVAE.