Chen Amiraz

Chen Amiraz, Robert Krauthgamer, Boaz Nadler

We study distributed schemes for high-dimensional sparse linear regression, based on orthogonal matching pursuit (OMP). Such schemes are particularly suited for settings where a central fusion center is connected to end machines, that have both computation and communication limitations. We prove that under suitable assumptions, distributed-OMP schemes recover the support of the regression vector with communication per machine linear in its sparsity and logarithmic in the dimension. Remarkably, this holds even at low signal-to-noise-ratios, where individual machines are unable to detect the support. Our simulations show that distributed-OMP schemes are competitive with more computationally intensive methods, and in some cases even outperform them.

Chen Amiraz, Florin Cuconasu, Simone Filice et al.

A well-known issue with Retrieval Augmented Generation (RAG) is that retrieved passages that are irrelevant to the query sometimes distract the answer-generating LLM, causing it to provide an incorrect response. In this paper, we shed light on this core issue and formulate the distracting effect of a passage w.r.t. a query (and an LLM). We provide a quantifiable measure of the distracting effect of a passage and demonstrate its robustness across LLMs. Our research introduces novel methods for identifying and using hard distracting passages to improve RAG systems. By fine-tuning LLMs with these carefully selected distracting passages, we achieve up to a 7.5% increase in answering accuracy compared to counterparts fine-tuned on conventional RAG datasets. Our contribution is two-fold: first, we move beyond the simple binary classification of irrelevant passages as either completely unrelated vs. distracting, and second, we develop and analyze multiple methods for finding hard distracting passages. To our knowledge, no other research has provided such a comprehensive framework for identifying and utilizing hard distracting passages.

Chen Amiraz, Yaroslav Fyodorov, Elad Haramaty et al.

Cross-lingual retrieval-augmented generation (RAG) is a critical capability for retrieving and generating answers across languages. Prior work in this context has mostly focused on generation and relied on benchmarks derived from open-domain sources, most notably Wikipedia. In such settings, retrieval challenges often remain hidden due to language imbalances, overlap with pretraining data, and memorized content. To address this gap, we study Arabic-English RAG in a domain-specific setting using benchmarks derived from real-world corporate datasets. Our benchmarks include all combinations of languages for the user query and the supporting document, drawn independently and uniformly at random. This enables a systematic study of multilingual retrieval behavior. Our findings reveal that retrieval is a critical bottleneck in cross-lingual domain-specific scenarios, with substantial performance drops occurring when the user query and supporting document languages differ. A key insight is that these failures stem primarily from the retriever's difficulty in ranking documents across languages. Finally, we propose two simple retrieval strategies that address this source of failure by enforcing equal retrieval from both languages or by translating the query, resulting in substantial improvements in cross-lingual and overall performance. These results highlight meaningful opportunities for improving multilingual retrieval, particularly in practical, real-world RAG applications.

Dan Greenstein, Zohar Karnin, Chen Amiraz et al.

The construction of function calling agents has emerged as a promising avenue for extending model capabilities. A major challenge for this task is obtaining high quality diverse data for training. Prior work emphasizes diversity in functions, invocation patterns, and interaction turns, yet linguistic diversity of requests and coverage of arguments (e.g., \texttt{city\_name}, \texttt{stock\_ticker}) remain underexplored. We propose a method that generates synthetic datasets via optimizing general-purpose diversity metrics across both queries and arguments, without relying on hand-crafted rules or taxonomies, making it robust to different usecases. We demonstrate the effectiveness of our technique via both intrinsic and extrinsic testing, comparing it to SoTA data generation methods. We show a superiority over baselines in terms of diversity, while keeping comparable correctness. Additionally, when used as a training set, the model resulting from our dataset exhibits superior performance compared to analogous models based on the baseline data generation methods in out-of-distribution performance. In particular, we achieve an $7.4\%$ increase in accuracy on the BFCL benchmark compared to similar counterparts.

Chen Amiraz, Robert Krauthgamer, Boaz Nadler

We consider the problem of sparse normal means estimation in a distributed setting with communication constraints. We assume there are $M$ machines, each holding $d$-dimensional observations of a $K$-sparse vector $μ$ corrupted by additive Gaussian noise. The $M$ machines are connected in a star topology to a fusion center, whose goal is to estimate the vector $μ$ with a low communication budget. Previous works have shown that to achieve the centralized minimax rate for the $\ell_2$ risk, the total communication must be high - at least linear in the dimension $d$. This phenomenon occurs, however, at very weak signals. We show that at signal-to-noise ratios (SNRs) that are sufficiently high - but not enough for recovery by any individual machine - the support of $μ$ can be correctly recovered with significantly less communication. Specifically, we present two algorithms for distributed estimation of a sparse mean vector corrupted by either Gaussian or sub-Gaussian noise. We then prove that above certain SNR thresholds, with high probability, these algorithms recover the correct support with total communication that is sublinear in the dimension $d$. Furthermore, the communication decreases exponentially as a function of signal strength. If in addition $KM\ll \tfrac{d}{\log d}$, then with an additional round of sublinear communication, our algorithms achieve the centralized rate for the $\ell_2$ risk. Finally, we present simulations that illustrate the performance of our algorithms in different parameter regimes.