Michal Shmueli-Scheuer

Elron Bandel, Ranit Aharonov, Michal Shmueli-Scheuer et al. · ibm-research

Paraphrase generation has been widely used in various downstream tasks. Most tasks benefit mainly from high quality paraphrases, namely those that are semantically similar to, yet linguistically diverse from, the original sentence. Generating high-quality paraphrases is challenging as it becomes increasingly hard to preserve meaning as linguistic diversity increases. Recent works achieve nice results by controlling specific aspects of the paraphrase, such as its syntactic tree. However, they do not allow to directly control the quality of the generated paraphrase, and suffer from low flexibility and scalability. Here we propose $QCPG$, a quality-guided controlled paraphrase generation model, that allows directly controlling the quality dimensions. Furthermore, we suggest a method that given a sentence, identifies points in the quality control space that are expected to yield optimal generated paraphrases. We show that our method is able to generate paraphrases which maintain the original meaning while achieving higher diversity than the uncontrolled baseline. The models, the code, and the data can be found in https://github.com/IBM/quality-controlled-paraphrase-generation.

Yotam Perlitz, Ariel Gera, Ofir Arviv et al. · ibm-research

Recent advancements in Language Models (LMs) have catalyzed the creation of multiple benchmarks, designed to assess these models' general capabilities. A crucial task, however, is assessing the validity of the benchmarks themselves. This is most commonly done via Benchmark Agreement Testing (BAT), where new benchmarks are validated against established ones using some agreement metric (e.g., rank correlation). Despite the crucial role of BAT for benchmark builders and consumers, there are no standardized procedures for such agreement testing. This deficiency can lead to invalid conclusions, fostering mistrust in benchmarks and upending the ability to properly choose the appropriate benchmark to use. By analyzing over 40 prominent benchmarks, we demonstrate how some overlooked methodological choices can significantly influence BAT results, potentially undermining the validity of conclusions. To address these inconsistencies, we propose a set of best practices for BAT and demonstrate how utilizing these methodologies greatly improves BAT robustness and validity. To foster adoption and facilitate future research,, we introduce BenchBench, a python package for BAT, and release the BenchBench-leaderboard, a meta-benchmark designed to evaluate benchmarks using their peers. Our findings underscore the necessity for standardized BAT, ensuring the robustness and validity of benchmark evaluations in the evolving landscape of language model research. BenchBench Package: github.com/IBM/BenchBench Leaderboard: hf.co/spaces/IBM/BenchBench

Yotam Perlitz, Elron Bandel, Ariel Gera et al. · ibm-research

The increasing versatility of language models (LMs) has given rise to a new class of benchmarks that comprehensively assess a broad range of capabilities. Such benchmarks are associated with massive computational costs, extending to thousands of GPU hours per model. However, the efficiency aspect of these evaluation efforts had raised little discussion in the literature. In this work, we present the problem of Efficient Benchmarking, namely, intelligently reducing the computation costs of LM evaluation without compromising reliability. Using the HELM benchmark as a test case, we investigate how different benchmark design choices affect the computation-reliability trade-off. We propose to evaluate the reliability of such decisions, by using a new measure -- Decision Impact on Reliability, DIoR for short. We find, for example, that a benchmark leader may change by merely removing a low-ranked model from the benchmark, and observe that a correct benchmark ranking can be obtained by considering only a fraction of the evaluation examples. Based on our findings, we outline a set of concrete recommendations for efficient benchmark design and utilization practices. To take a step further, we use our findings to propose an evaluation algorithm, that, when applied to the HELM benchmark, leads to dramatic cost savings with minimal loss of benchmark reliability, often reducing computation by x100 or more.

Elron Bandel, Asaf Yehudai, Lilach Eden et al. · ibm-research

The promise of general-purpose agents - systems that perform tasks in unfamiliar environments without domain-specific engineering - remains largely unrealized. Existing agents are predominantly specialized, and while emerging implementations like OpenAI SDK Agent and Claude Code hint at broader capabilities, no systematic evaluation of their general performance has been pursued. Current agentic benchmarks assume domain-specific integration, encoding task information in ways that preclude fair evaluation of general agents. This paper frames general-agent evaluation as a first-class research objective. We propose conceptual principles for such evaluation, a Unified Protocol enabling agent-benchmark integration, and Exgentic - a practical framework for general agent evaluation. We benchmark five prominent agent implementations across six environments as the first Open General Agent Leaderboard. Our experiments show that general agents generalize across diverse environments, achieving performance comparable to domain-specific agents without any environment-specific tuning. We release our evaluation protocol, framework, and leaderboard to establish a foundation for systematic research on general-purpose agents.

Alon Halfon, Shai Gretz, Ofir Arviv et al.

Fine-tuning Large Language Models (LLMs) is an effective method to enhance their performance on downstream tasks. However, choosing the appropriate setting of tuning hyperparameters (HPs) is a labor-intensive and computationally expensive process. Here, we provide recommended HP configurations for practical use-cases that represent a better starting point for practitioners, when considering two SOTA LLMs and two commonly used tuning methods. We describe Coverage-based Search (CBS), a process for ranking HP configurations based on an offline extensive grid search, such that the top ranked configurations collectively provide a practical robust recommendation for a wide range of datasets and domains. We focus our experiments on Llama-3-8B and Mistral-7B, as well as full fine-tuning and LoRa, conducting a total of > 10,000 tuning experiments. Our results suggest that, in general, Llama-3-8B and LoRA should be preferred, when possible. Moreover, we show that for both models and tuning methods, exploring only a few HP configurations, as recommended by our analysis, can provide excellent results in practice, making this work a valuable resource for practitioners.

Tomer Keren, Nitay Calderon, Asaf Yehudai et al.

As agent capabilities advance, existing benchmarks, such as $τ^2$-Bench, are becoming increasingly saturated. Yet constructing new benchmark tasks remains complex, costly, and labor-intensive. Moreover, the standard approach, in which scenarios are first written in natural language and then mapped to tool sequences, captures only a narrow subset of the tool-use patterns agents exercise. In this paper, we address these problems by reversing the task construction process. We propose TASTE: Task Synthesis from Tool Sequence Evolution, an automatic method that generates challenging tasks with broader tool-use coverage. TASTE utilizes an Adaptive Contrastive $n$-gram model trained on LLM-judged validity signals. This enables sampling valid tool sequences that cover a vast range of tool combinations. TASTE then selects representative sequences from the pool via clustering, instantiates them into complete benchmark tasks, and refines them through iterative difficulty evolution. Using TASTE, we construct $τ^c$-Bench, a challenging extension of the three domains of $τ^2$-Bench. We evaluate $11$ agent/user LLM pairs and find that models nearly saturating $τ^2$-Bench suffer severe performance drops on our tasks (e.g., Gemini-3-Flash falls from $0.82\!-\!0.94$ to $0.28\!-\!0.61$). Beyond increasing difficulty, our generated tasks more than double the number of unique tool combinations agents must execute. Our results suggest high scores on existing benchmarks often reflect saturation rather than robust task-solving ability. By automating the generation of difficult, high-coverage benchmarks, TASTE enables continuous, scalable evaluation of future agents.

Yotam Perlitz, Dafna Sheinwald, Noam Slonim et al.

We present nBIIG, a neural Business Intelligence (BI) Insights Generation system. Given a table, our system applies various analyses to create corresponding RDF representations, and then uses a neural model to generate fluent textual insights out of these representations. The generated insights can be used by an analyst, via a human-in-the-loop paradigm, to enhance the task of creating compelling table reports. The underlying generative neural model is trained over large and carefully distilled data, curated from multiple BI domains. Thus, the system can generate faithful and fluent insights over open-domain tables, making it practical and useful.

Shir Ashury-Tahan, Yifan Mai, Elron Bandel et al. · ibm-research

Large Language Models (LLM) benchmarks tell us when models fail, but not why they fail. A wrong answer on a reasoning dataset may stem from formatting issues, calculation errors, or dataset noise rather than weak reasoning. Without disentangling such causes, benchmarks remain incomplete and cannot reliably guide model improvement. We introduce ErrorMap, the first method to chart the sources of LLM failure. It extracts a model's unique "failure signature", clarifies what benchmarks measure, and broadens error identification to reduce blind spots. This helps developers debug models, aligns benchmark goals with outcomes, and supports informed model selection. ErrorMap works on any model or dataset with the same logic. Applying our method to 35 datasets and 83 models we generate ErrorAtlas, a taxonomy of model errors, revealing recurring failure patterns. ErrorAtlas highlights error types that are currently underexplored in LLM research, such as omissions of required details in the output and question misinterpretation. By shifting focus from where models succeed to why they fail, ErrorMap and ErrorAtlas enable advanced evaluation - one that exposes hidden weaknesses and directs progress. Unlike success, typically measured by task-level metrics, our approach introduces a deeper evaluation layer that can be applied globally across models and tasks, offering richer insights into model behavior and limitations. We make the taxonomy and code publicly available with plans to periodically update ErrorAtlas as new benchmarks and models emerge.

Alexandre Lacoste, Nicolas Gontier, Oleh Shliazhko et al. · ibm-research

The proliferation of agent benchmarks has created critical fragmentation that threatens research productivity. Each new benchmark requires substantial custom integration, creating an "integration tax" that limits comprehensive evaluation. We propose CUBE (Common Unified Benchmark Environments), a universal protocol standard built on MCP and Gym that allows benchmarks to be wrapped once and used everywhere. By separating task, benchmark, package, and registry concerns into distinct API layers, CUBE enables any compliant platform to access any compliant benchmark for evaluation, RL training, or data generation without custom integration. We call on the community to contribute to the development of this standard before platform-specific implementations deepen fragmentation as benchmark production accelerates through 2026.

Yotam Perlitz, Liat Ein-Dor, Dafna Sheinwald et al.

Generating natural language statements to convey logical inferences from tabular data (i.e., Logical NLG) is a process with one input and a variety of valid outputs. This characteristic underscores the need for a method to produce a diverse set of valid outputs, presenting different perspectives of the input data. We propose a simple yet effective diversity-enhancing scheme that builds upon an inherent property of the statements, their logic-types, by using a type-controlled table-to-text generation model. We demonstrate, through extensive automatic and human evaluations over the two publicly available Logical NLG datasets, that our proposed method both facilitates the ability to effectively control the generated statement type, and produces results superior to the strongest baselines in terms of quality and factuality-diversity trade-off.

Asaf Yehudai, Lilach Eden, Michal Shmueli-Scheuer

Agentic systems are becoming more capable: agents define strategies, take actions, and interact with different environments. This autonomy poses serious challenges for overseeing and assessing agent behavior. Most current tools are limited, focusing on observability with basic evaluation capabilities or imposing static, hand-crafted error taxonomies that cannot adapt to new domains. To address this gap, we present Agentic CLEAR, an automatic, dynamic, and easy-to-use evaluation framework. It produces textual insights into the agent behavior on three levels of granularity: system, trace, and node. Agentic CLEAR operates above the observability layer, enabling seamless integration and featuring an intuitive UI that makes agent evaluation highly accessible. In our experiments on four benchmarks, seven agentic settings, and tens of thousands of LLM calls, we show that Agentic CLEAR produces high-quality, data-driven, insightful feedback. Our analysis shows strong alignment with human-annotated errors and the ability to predict task success rate.

Leyao Wang, Yanan He, Peng Chen et al.

Deep research agents increasingly automate complex information-seeking tasks, producing evidence-grounded reports via multi-step reasoning, tool use, and synthesis. Their growing role demands scalable, reliable evaluation, positioning LLM-as-judge as a supervision paradigm for assessing factual accuracy, evidence use, and reasoning quality. Yet the reliability of these judges for deep research agents remains poorly understood, posing a critical meta-evaluation problem: before deploying LLM judges to supervise research agents, we must first evaluate the judges themselves. Existing meta-evaluations fall short in two ways: (1) reliance on coarse, subjective human-preference agreement; (2) focus on instruction-following or verifiable tasks, leaving open-ended agent executions unexplored. To address these gaps, we introduce REFLECT (REliable Fine-grained LLM judge Evaluation via Controlled inTervention), a meta-evaluation benchmark targeting fine-grained failure detection in agentic environments. REFLECT defines a detailed taxonomy of process- and outcome-level failure modes, instantiated by performing controlled and localized interventions on quality-screened agent execution traces. This yields verifiable, comprehensive, and fine-grained instances for validating the judge models. Our experiments show that current LLM judges remain unreliable: even the best-performing models achieve overall accuracies below 55% across reasoning, tool-use, and report-quality failures, with especially poor performance on evidence verification. Together, our taxonomy and findings expose systematic judge limitations, reveal tradeoffs in cost and reliability, and offer actionable guidance for building more reliable evaluation pipelines for deep research agents.

Shir Ashury-Tahan, Ariel Gera, Elron Bandel et al.

Robustness is often regarded as a critical future challenge for real-world applications, where stability is essential. However, as models often learn tasks in a similar order, we hypothesize that easier tasks will be easier regardless of how they are presented to the model. Indeed, in this paper, we show that as models approach high performance on a task, robustness is effectively achieved. Through an empirical analysis of multiple models across diverse datasets and configurations (e.g., paraphrases, different temperatures), we find a strong positive correlation. Moreover, we find that robustness is primarily driven by task-specific competence rather than inherent model-level properties, challenging current approaches that treat robustness as an independent capability. Thus, from a high-level perspective, we may expect that as new tasks saturate, model robustness on these tasks will emerge accordingly. For researchers, this implies that explicit efforts to measure and improve robustness may warrant reduced emphasis, as such robustness is likely to develop alongside performance gains. For practitioners, it acts as a sign that indeed the tasks that the literature deals with are unreliable, but on easier past tasks, the models are reliable and ready for real-world deployment.

Eliya Habba, Itay Itzhak, Asaf Yehudai et al.

The rapid release of both language models and benchmarks makes it increasingly costly to evaluate every model on every dataset. In practice, models are often evaluated on different samples, making scores difficult to compare across studies. To address this, we propose a framework based on multidimensional Item Response Theory (IRT) that uses anchor items to calibrate new benchmarks to the evaluation suite while holding previously calibrated item parameters fixed. Our approach supports a realistic evaluation setting in which datasets are introduced over time and models are evaluated only on the datasets available at the time of evaluation, while a fixed anchor set for each dataset is used so that results from different evaluation periods can be compared directly. In large-scale experiments on more than $400$ models, our framework predicts full-evaluation performance within 2-3 percentage points using only $100$ anchor questions per dataset, with Spearman $ρ\geq 0.9$ for ranking preservation, showing that it is possible to extend benchmark suites over time while preserving score comparability, at a constant evaluation cost per new dataset. Code available at https://github.com/eliyahabba/growing-pains

Asaf Yehudai, Lilach Eden, Yotam Perlitz et al.

The evaluation of Large Language Models (LLMs) increasingly relies on other LLMs acting as judges. However, current evaluation paradigms typically yield a single score or ranking, answering which model is better but not why. While essential for benchmarking, these top-level scores obscure the specific, actionable reasons behind a model's performance. To bridge this gap, we introduce CLEAR, an interactive, open-source package for LLM-based error analysis. CLEAR first generates per-instance textual feedback, then it creates a set of system-level error issues, and quantifies the prevalence of each identified issue. Our package also provides users with an interactive dashboard that allows for a comprehensive error analysis through aggregate visualizations, applies interactive filters to isolate specific issues or score ranges, and drills down to the individual instances that exemplify a particular behavioral pattern. We demonstrate CLEAR analysis for RAG and Math benchmarks, and showcase its utility through a user case study.

Elron Bandel, Yotam Perlitz, Elad Venezian et al.

In the dynamic landscape of generative NLP, traditional text processing pipelines limit research flexibility and reproducibility, as they are tailored to specific dataset, task, and model combinations. The escalating complexity, involving system prompts, model-specific formats, instructions, and more, calls for a shift to a structured, modular, and customizable solution. Addressing this need, we present Unitxt, an innovative library for customizable textual data preparation and evaluation tailored to generative language models. Unitxt natively integrates with common libraries like HuggingFace and LM-eval-harness and deconstructs processing flows into modular components, enabling easy customization and sharing between practitioners. These components encompass model-specific formats, task prompts, and many other comprehensive dataset processing definitions. The Unitxt-Catalog centralizes these components, fostering collaboration and exploration in modern textual data workflows. Beyond being a tool, Unitxt is a community-driven platform, empowering users to build, share, and advance their pipelines collaboratively. Join the Unitxt community at https://github.com/IBM/unitxt!

Asaf Yehudai, Lilach Eden, Alan Li et al.

The emergence of LLM-based agents represents a paradigm shift in AI, enabling autonomous systems to plan, reason, use tools, and maintain memory while interacting with dynamic environments. This paper provides the first comprehensive survey of evaluation methodologies for these increasingly capable agents. We systematically analyze evaluation benchmarks and frameworks across four critical dimensions: (1) fundamental agent capabilities, including planning, tool use, self-reflection, and memory; (2) application-specific benchmarks for web, software engineering, scientific, and conversational agents; (3) benchmarks for generalist agents; and (4) frameworks for evaluating agents. Our analysis reveals emerging trends, including a shift toward more realistic, challenging evaluations with continuously updated benchmarks. We also identify critical gaps that future research must address-particularly in assessing cost-efficiency, safety, and robustness, and in developing fine-grained, and scalable evaluation methods. This survey maps the rapidly evolving landscape of agent evaluation, reveals the emerging trends in the field, identifies current limitations, and proposes directions for future research.

Eliya Habba, Ofir Arviv, Itay Itzhak et al. · ibm-research

Recent work found that LLMs are sensitive to a wide range of arbitrary prompt dimensions, including the type of delimiters, answer enumerators, instruction wording, and more. This throws into question popular single-prompt evaluation practices. We present DOVE (Dataset Of Variation Evaluation) a large-scale dataset containing prompt perturbations of various evaluation benchmarks. In contrast to previous work, we examine LLM sensitivity from an holistic perspective, and assess the joint effects of perturbations along various dimensions, resulting in thousands of perturbations per instance. We evaluate several model families against DOVE, leading to several findings, including efficient methods for choosing well-performing prompts, observing that few-shot examples reduce sensitivity, and identifying instances which are inherently hard across all perturbations. DOVE consists of more than 250M prompt perturbations and model outputs, which we make publicly available to spur a community-wide effort toward meaningful, robust, and efficient evaluation. Browse the data, contribute, and more: https://slab-nlp.github.io/DOVE/

Shir Ashury-Tahan, Yifan Mai, Rajmohan C et al. · ibm-research, stanford

Despite its real-world significance, model performance on tabular data remains underexplored, leaving uncertainty about which model to rely on and which prompt configuration to adopt. To address this gap, we create ToRR, a benchmark for Table Reasoning and Robustness, measuring model performance and robustness on table-related tasks. The benchmark includes 10 datasets that cover different types of table reasoning capabilities across varied domains. ToRR goes beyond model performance rankings, and is designed to reflect whether models can handle tabular data consistently and robustly, across a variety of common table representation formats. We present a leaderboard as well as comprehensive analyses of the results of leading models over ToRR. Our results reveal a striking pattern of brittle model behavior, where even strong models are unable to perform robustly on tabular data tasks. Although no specific table format leads to consistently better performance, we show that testing over multiple formats is crucial for reliably estimating model capabilities. Moreover, we show that the reliability boost from testing multiple prompts can be equivalent to adding more test examples. Overall, our findings show that table understanding and reasoning tasks remain a significant challenge.

George Kour, Itay Nakash, Ateret Anaby-Tavor et al. · ibm-research

As Large Language Models (LLMs) become deeply integrated into human life and increasingly influence decision-making, it's crucial to evaluate whether and to what extent they exhibit subjective preferences, opinions, and beliefs. These tendencies may stem from biases within the models, which may shape their behavior, influence the advice and recommendations they offer to users, and potentially reinforce certain viewpoints. This paper presents the Preference, Opinion, and Belief survey (POBs), a benchmark developed to assess LLMs' subjective inclinations across societal, cultural, ethical, and personal domains. We applied our benchmark to evaluate leading open- and closed-source LLMs, measuring desired properties such as reliability, neutrality, and consistency. In addition, we investigated the effect of increasing the test-time compute, through reasoning and self-reflection mechanisms, on those metrics. While effective in other tasks, our results show that these mechanisms offer only limited gains in our domain. Furthermore, we reveal that newer model versions are becoming less consistent and more biased toward specific viewpoints, highlighting a blind spot and a concerning trend. POBS: https://ibm.github.io/POBS

Yotam Perlitz, Ariel Gera, Michal Shmueli-Scheuer et al.

The field of Natural Language Generation (NLG) suffers from a severe shortage of labeled data due to the extremely expensive and time-consuming process involved in manual annotation. A natural approach for coping with this problem is active learning (AL), a well-known machine learning technique for improving annotation efficiency by selectively choosing the most informative examples to label. However, while AL has been well-researched in the context of text classification, its application to NLG remains largely unexplored. In this paper, we present a first systematic study of active learning for NLG, considering a diverse set of tasks and multiple leading selection strategies, and harnessing a strong instruction-tuned model. Our results indicate that the performance of existing AL strategies is inconsistent, surpassing the baseline of random example selection in some cases but not in others. We highlight some notable differences between the classification and generation scenarios, and analyze the selection behaviors of existing AL strategies. Our findings motivate exploring novel approaches for applying AL to generation tasks.

Odellia Boni, Guy Feigenblat, Guy Lev et al.

We present HowSumm, a novel large-scale dataset for the task of query-focused multi-document summarization (qMDS), which targets the use-case of generating actionable instructions from a set of sources. This use-case is different from the use-cases covered in existing multi-document summarization (MDS) datasets and is applicable to educational and industrial scenarios. We employed automatic methods, and leveraged statistics from existing human-crafted qMDS datasets, to create HowSumm from wikiHow website articles and the sources they cite. We describe the creation of the dataset and discuss the unique features that distinguish it from other summarization corpora. Automatic and human evaluations of both extractive and abstractive summarization models on the dataset reveal that there is room for improvement.

Guy Lev, Michal Shmueli-Scheuer, Achiya Jerbi et al.

Frequently Asked Questions (FAQ) webpages are created by organizations for their users. FAQs are used in several scenarios, e.g., to answer user questions. On the other hand, the content of FAQs is affected by user questions by definition. In order to promote research in this field, several FAQ datasets exist. However, we claim that being collected from community websites, they do not correctly represent challenges associated with FAQs in an organizational context. Thus, we release orgFAQ, a new dataset composed of $6988$ user questions and $1579$ corresponding FAQs that were extracted from organizations' FAQ webpages in the Jobs domain. In this paper, we provide an analysis of the properties of such FAQs, and demonstrate the usefulness of our new dataset by utilizing it in a relevant task from the Jobs domain. We also show the value of the orgFAQ dataset in a task of a different domain - the COVID-19 pandemic.

Shai Erera, Michal Shmueli-Scheuer, Guy Feigenblat et al.

We present a novel system providing summaries for Computer Science publications. Through a qualitative user study, we identified the most valuable scenarios for discovery, exploration and understanding of scientific documents. Based on these findings, we built a system that retrieves and summarizes scientific documents for a given information need, either in form of a free-text query or by choosing categorized values such as scientific tasks, datasets and more. Our system ingested 270,000 papers, and its summarization module aims to generate concise yet detailed summaries. We validated our approach with human experts.

Guy Lev, Michal Shmueli-Scheuer, Jonathan Herzig et al.

Currently, no large-scale training data is available for the task of scientific paper summarization. In this paper, we propose a novel method that automatically generates summaries for scientific papers, by utilizing videos of talks at scientific conferences. We hypothesize that such talks constitute a coherent and concise description of the papers' content, and can form the basis for good summaries. We collected 1716 papers and their corresponding videos, and created a dataset of paper summaries. A model trained on this dataset achieves similar performance as models trained on a dataset of summaries created manually. In addition, we validated the quality of our summaries by human experts.

Tommy Sandbank, Michal Shmueli-Scheuer, Jonathan Herzig et al.

Virtual agents are becoming a prominent channel of interaction in customer service. Not all customer interactions are smooth, however, and some can become almost comically bad. In such instances, a human agent might need to step in and salvage the conversation. Detecting bad conversations is important since disappointing customer service may threaten customer loyalty and impact revenue. In this paper, we outline an approach to detecting such egregious conversations, using behavioral cues from the user, patterns in agent responses, and user-agent interaction. Using logs of two commercial systems, we show that using these features improves the detection F1-score by around 20% over using textual features alone. In addition, we show that those features are common across two quite different domains and, arguably, universal.