Papers by Zorik Gekhman
Fine-Grained Detection of Context-Grounded Hallucinations Using LLMs (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing representations of hallucinations limit the types of errors that can be expressed, so we propose a new representation based on free-form textual descriptions, capturing the full range of possible errors. |
| Approach: | They propose a benchmark for localizing hallucinations using LLMs with a human annotation of over 1,000 examples and a protocol to verify its quality in a humans evaluation. |
| Outcome: | The proposed representation captures the full range of possible errors, and the best model achieves an F1 score of 0.67. |
Can LLMs Learn Macroeconomic Narratives from Social Media? (2025.findings-naacl)
Copied to clipboard
| Challenge: | Existing evaluation strategies for analyzing economic data with narratives are limited due to the complexity of the interplay of numerous factors and the difficulty in isolating causal relationships. |
| Approach: | They propose to use two Twitter datasets to capture economy-related narratives and use them to construct models using large language models. |
| Outcome: | The proposed models are able to predict macroeconomic fluctuations using the extracted or extracted narratives in two Twitter datasets. |
Confidence Improves Self-Consistency in LLMs (2025.findings-acl)
Copied to clipboard
| Challenge: | Modern large language models (LLMs) demonstrate strong reasoning capabilities, driven in part by their capacity to generate a sequence of intermediate reasoning steps that lead them toward a final answer. |
| Approach: | They propose a method that performs a weighted majority vote based on confidence scores obtained directly from the model. |
| Outcome: | The proposed method outperforms self-consistency on nine models and four datasets, reducing the required number of reasoning paths by over 40% on average. |
On the Robustness of Dialogue History Representation in Conversational Question Answering: A Comprehensive Study and a New Prompt-based Method (2023.tacl-1)
Copied to clipboard
| Challenge: | Existing models show impressive results on a common CQA benchmark, but are they robust to domain, setting and domain? |
| Approach: | They propose a prompt-based history modeling approach that adds textual prompts directly to the text of a passage. |
| Outcome: | The proposed model is simple, easy to plug into practically any model and highly effective. |
RED-ACE: Robust Error Detection for ASR using Confidence Embeddings (2022.emnlp-main)
Copied to clipboard
| Challenge: | ASR Error Detection (AED) models post-process the output of Automatic Speech Recognition systems, in order to detect transcription errors. |
| Approach: | They propose to use ASR model's word-level confidence scores to combine ASR models with transcribed text to improve AED performance. |
| Outcome: | The proposed models combine the confidence scores and transcribed text into a contextualized representation. |
KoBE: Knowledge-Based Machine Translation Evaluation (2020.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods for machine translation evaluation do not require reference translations. |
| Approach: | They propose a method for machine translation evaluation which does not require reference translations. |
| Outcome: | The proposed method achieves highest correlation with human judgements on 9 out of 18 language pairs from the WMT19 benchmark for evaluation without references. |
Does Fine-Tuning LLMs on New Knowledge Encourage Hallucinations? (2024.emnlp-main)
Copied to clipboard
| Challenge: | Pre-training Large Language Models (LLMs) on textual corpora embeds substantial factual knowledge in their parameters, which is essential for excelling in various downstream applications. |
| Approach: | They propose to use supervised fine-tuning to align large language models to new factual information that is not acquired through pre-training. |
| Outcome: | The proposed model is trained to generate facts that are not grounded in pre-existing knowledge, but hallucinates when examples with new knowledge are learned. |
TrueTeacher: Learning Factual Consistency Evaluation with Large Language Models (2023.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods for evaluating factual consistency are limited in their effectiveness. |
| Approach: | They propose a method for generating synthetic data by annotating diverse model-generated summaries using a LLM. |
| Outcome: | The proposed method outperforms state-of-the-art models and the LLM teacher on TRUE benchmarks. |
Measuring the Robustness of NLP Models to Domain Shifts (2024.findings-emnlp)
Copied to clipboard
Nitay Calderon, Naveh Porat, Eyal Ben-David, Alexander Chapanin, Zorik Gekhman, Nadav Oved, Vitaly Shalumov, Roi Reichart
| Challenge: | Existing research on domain robustness (DR) relies on the Source Drop (SD) but lacks a complementary metric, a new study finds . |
| Approach: | They propose to use the Target Drop (TD) to measure domain DR . they use a DR benchmark consisting of 7 diverse tasks to measure both metrics . |
| Outcome: | The proposed model types excel in-domain, but few-shot LLMs often surpass them cross-domain showing better robustness. |