31 citations · 108 across the 26 of their papers we have counts for
28 papers
Where Should a Document Live: Context, Representations, or Parameters?
Nathanaël Carraz Rakotonirina, Momchil Hardalov, Gonzalo Iglesias +1
To answer questions outside of their pre-training data, large language models (LLMs) need access to new information, which can be presented in the context window as documents, enco…
Cartridges at Scale: Training Modular KV Caches over Large Document Collections
Momchil Hardalov, Gonzalo Iglesias, Adrià de Gispert
Large Language Models can reason over long contexts, yet prefilling millions of tokens is wasteful as much of the content remains static across queries. Cartridges address this by…
DeepFact: Co-Evolving Benchmarks and Agents for Deep Research Factuality
Yukun Huang, Leonardo F. R. Ribeiro, Momchil Hardalov +3
Search-augmented LLM agents can produce deep research reports (DRRs), but verifying claim-level factuality remains challenging. Existing fact-checkers are primarily designed for ge…
Exploring Fine-Tuning for In-Context Retrieval and Efficient KV-Caching in Long-Context Language Models
Francesco Maria Molfese, Momchil Hardalov, Rexhina Blloshmi +2
With context windows of millions of tokens, Long-Context Language Models (LCLMs) can encode entire document collections, offering a strong alternative to conventional retrieval-aug…
Correct, Concise and Complete: Multi-stage Training For Adaptive Reasoning
Nathanaël Carraz Rakotonirina, Ren Pang, Neha Anna John +2
The reasoning capabilities of large language models (LLMs) have improved substantially through increased test-time computation, typically in the form of intermediate tokens known a…
Understanding and Improving Information Preservation in Prompt Compression for LLMs
Weronika Łajewska, Momchil Hardalov, Laura Aina +3
Recent advancements in large language models (LLMs) have enabled their successful application to a broad range of tasks. However, in information-intensive tasks, the prompt length…
Post-OCR Text Correction for Bulgarian Historical Documents
Angel Beshirov, Milena Dobreva, Dimitar Dimitrov +3
The digitization of historical documents is crucial for preserving the cultural heritage of the society. An important step in this process is converting scanned images to text usin…
Factual Confidence of LLMs: on Reliability and Robustness of Current Estimators
Matéo Mahaut, Laura Aina, Paula Czarnowska +3
Large Language Models (LLMs) tend to be unreliable in the factuality of their answers. To address this problem, NLP researchers have proposed a range of techniques to estimate LLM'…
DEM: Distribution Edited Model for Training with Mixed Data Distributions
Dhananjay Ram, Aditya Rawal, Momchil Hardalov +2
Training with mixed data distributions is a common and important part of creating multi-task and instruction-following models. The diversity of the data distributions and cost of j…
bgGLUE: A Bulgarian General Language Understanding Evaluation Benchmark
Momchil Hardalov, Pepa Atanasova, Todor Mihaylov +7
We present bgGLUE(Bulgarian General Language Understanding Evaluation), a benchmark for evaluating language models on Natural Language Understanding (NLU) tasks in Bulgarian. Our b…
Detecting Check-Worthy Claims in Political Debates, Speeches, and Interviews Using Audio Data
Petar Ivanov, Ivan Koychev, Momchil Hardalov +1
Developing tools to automatically detect check-worthy claims in political debates and speeches can greatly help moderators of debates, journalists, and fact-checkers. While previou…
Diable: Efficient Dialogue State Tracking as Operations on Tables
Pietro Lesci, Yoshinari Fujinuma, Momchil Hardalov +3
Sequence-to-sequence state-of-the-art systems for dialogue state tracking (DST) use the full dialogue history as input, represent the current state as a list with all the slots, an…
CrowdChecked: Detecting Previously Fact-Checked Claims in Social Media
Momchil Hardalov, Anton Chernyavskiy, Ivan Koychev +2
While there has been substantial progress in developing systems to automate fact-checking, they still lack credibility in the eyes of the users. Thus, an interesting approach has e…
Leaf: Multiple-Choice Question Generation
Kristiyan Vachev, Momchil Hardalov, Georgi Karadzhov +3
Testing with quiz questions has proven to be an effective way to assess and improve the educational process. However, manually creating quizzes is tedious and time-consuming. To ad…
SUper Team at SemEval-2016 Task 3: Building a feature-rich system for community question answering
Tsvetomila Mihaylova, Pepa Gencheva, Martin Boyanov +9
We present the system we built for participating in SemEval-2016 Task 3 on Community Question Answering. We achieved the best results on subtask C, and strong results on subtasks A…
Few-Shot Cross-Lingual Stance Detection with Sentiment-Based Pre-Training
Momchil Hardalov, Arnav Arora, Preslav Nakov +1
The goal of stance detection is to determine the viewpoint expressed in a piece of text towards a target. These viewpoints or contexts are often expressed in many different languag…
Generating Answer Candidates for Quizzes and Answer-Aware Question Generators
Kristiyan Vachev, Momchil Hardalov, Georgi Karadzhov +3
In education, open-ended quiz questions have become an important tool for assessing the knowledge of students. Yet, manually preparing such questions is a tedious task, and thus au…
Cross-Domain Label-Adaptive Stance Detection
Momchil Hardalov, Arnav Arora, Preslav Nakov +1
Stance detection concerns the classification of a writer's viewpoint towards a target. There are different task variants, e.g., stance of a tweet vs. a full article, or stance with…
A Neighbourhood Framework for Resource-Lean Content Flagging
Sheikh Muhammad Sarwar, Dimitrina Zlatkova, Momchil Hardalov +3
We propose a novel framework for cross-lingual content flagging with limited target-language data, which significantly outperforms prior work in terms of predictive performance. Th…
A Survey on Stance Detection for Mis- and Disinformation Identification
Momchil Hardalov, Arnav Arora, Preslav Nakov +1
Understanding attitudes expressed in texts, also known as stance detection, plays an important role in systems for detecting false information online, be it misinformation (uninten…
Detecting Harmful Content On Online Platforms: What Platforms Need Vs. Where Research Efforts Go
Arnav Arora, Preslav Nakov, Momchil Hardalov +8
The proliferation of harmful content on online platforms is a major societal problem, which comes in many different forms including hate speech, offensive language, bullying and ha…
EXAMS: A Multi-Subject High School Examinations Dataset for Cross-Lingual and Multilingual Question Answering
Momchil Hardalov, Todor Mihaylov, Dimitrina Zlatkova +3
We propose EXAMS -- a new benchmark dataset for cross-lingual and multilingual question answering for high school examinations. We collected more than 24,000 high-quality high scho…
Enriched Pre-trained Transformers for Joint Slot Filling and Intent Detection
Momchil Hardalov, Ivan Koychev, Preslav Nakov
Detecting the user's intent and finding the corresponding slots among the utterance's words are important tasks in natural language understanding. Their interconnected nature makes…
In Search of Credible News
Momchil Hardalov, Ivan Koychev, Preslav Nakov
We study the problem of finding fake online news. This is an important problem as news of questionable credibility have recently been proliferating in social media at an alarming s…