Papers by Aviv Slobodkin

15 papers
PrefixNLI: Detecting Factual Inconsistencies as Soon as They Arise (2026.acl-long)

Copied to clipboard

Challenge: Large Language Models (LLMs) are prone to factually inconsistent statements, known as hallucinations.
Approach: They propose to train a specialized model that detects inconsistencies over text prefixes to improve generation faithfulness by 5-14 F1 points.
Outcome: The proposed model outperforms baseline models by 5-14 F1 points in prefix-level entailment.
Effective QA-Driven Annotation of Predicate–Argument Relations Across Languages (2026.eacl-long)

Copied to clipboard

Challenge: Explicit representations of predicate-argument relations are a cornerstone of natural language understanding.
Approach: They propose a cross-linguistic projection approach that reuses an English QA-SRL parser within a constrained translation and word-alignment pipeline to automatically generate question-answer annotations aligned with target-language predicates.
Outcome: The proposed approach outperforms strong multilingual LLMs in Hebrew, Russian, and French.
SummHelper: Collaborative Human-Computer Summarization (2023.emnlp-demo)

Copied to clipboard

Challenge: Existing approaches for text summarization are mostly automated, with limited space for human intervention and control.
Approach: They propose a 2-phase summarization assistant that facilitates human-machine collaboration . it suggests possible content and generates a coherent summary from these selections . authors hope to improve the efficiency of the computer and human-involved approach .
Outcome: The proposed summarization assistant is a 2-phase summarizing assistant . it suggests potential content and consolidates the output with visual mappings . the proposed system is available for free on youtube .
The Curious Case of Hallucinatory (Un)answerability: Finding Truths in the Hidden States of Over-Confident Large Language Models (2023.emnlp-main)

Copied to clipboard

Challenge: Large language models (LLMs) have been shown to possess impressive capabilities, but they are not problem-free.
Approach: They explore the behavior of large language models when presented with (un)answerable queries.
Outcome: The proposed models encode the answerability of an input query, the authors show . they also show that the first decoded token is a strong indicator .
Mediators in Determining what Processing BERT Performs First (2021.naacl-main)

Copied to clipboard

Challenge: Probing neural models for the ability to perform downstream tasks using their activation patterns is often used to localize what parts of the network specialize in performing which tasks.
Approach: They propose to consider the prediction’s context length as a potential mediating factor and consider the length of the span whose processing is minimally required to perform the prediction.
Outcome: The proposed model can get 196 different rankings when probing with seven tasks, the authors show .
Semantics-aware Attention Improves Neural Machine Translation (2022.starsem-1)

Copied to clipboard

Challenge: Existing attempts to integrate semantic structures into NMT Transformers have failed .
Approach: They propose two parameter-free methods for injecting semantic information into Transformers, using a Scene-Aware Self-Attention (SASA) head and a Scenario-Award Cross-Action (SACrA) head.
Outcome: The proposed methods improve on the vanilla Transformer and syntax-aware models for four language pairs and show an additional gain when using both semantic and syntactic structures in some language pairs.
Controlled Text Reduction (2022.emnlp-main)

Copied to clipboard

Challenge: Abstractive text summarization models separate the salience detection phase from the text generation phase.
Approach: They propose to formalize Controlled Text Reduction as a standalone task . they advocate the potential of such models for modular fully-automatic summarization .
Outcome: The proposed model shows that it is possible to produce a reduced version of a source text using decomposed modeling.
LAQuer: Localized Attribution Queries in Content-grounded Generation (2025.acl-long)

Copied to clipboard

Challenge: Existing attribution methods associate entire sentences with source documents, which can be overwhelming for users seeking to fact-check specific claims.
Approach: They propose a task that localizes selected spans of generated output to their corresponding source spans, allowing fine-grained and user-directed attribution.
Outcome: The proposed task localizes selected spans of generated output to their corresponding source spans, allowing fine-grained and user-directed attribution.
Where Did That Come From? Sentence-Level Error-Tolerant Attribution (2025.findings-emnlp)

Copied to clipboard

Challenge: Existing task definitions exclude unsupported or hallucinated content leaving them unattributed . authors propose a new definition for sentence-level error-tolerant attribution .
Approach: They propose a new definition for sentence-level error-tolerant attribution that extends attribution to include incorrect or hallucinated content.
Outcome: The proposed approach reduces annotation time and facilitates hallucination fixing.
Don’t Add, don’t Miss: Effective Content Preserving Generation from Pre-Selected Text Spans (2023.findings-emnlp)

Copied to clipboard

Challenge: Existing CTR models are mediocre and lack reliable performance . authors propose an explicit decomposition of these two subtasks into a single task .
Approach: They propose an isolated task that challenges models to generate coherent text conforming to pre-selected content within the input text ("highlights") authors propose a high-quality, open-source CTR model that tackles two prior key limitations: inadequate enforcement of the content-preservation constraint, and suboptimal silver training data.
Outcome: The proposed model significantly improves silver training data quality over the existing model, with up to 30 ROUGE-L points.
Is It Really Long Context if All You Need Is Retrieval? Towards Genuinely Difficult Long Context NLP (2024.emnlp-main)

Copied to clipboard

Challenge: Improvements in language models’ capabilities have pushed their applications towards longer contexts, making long-context evaluation and development an active research area.
Approach: They propose to unpack the taxonomy of long-context based on the properties that make them more difficult with longer contexts.
Outcome: The proposed taxonomy is based on the properties that make them more difficult with longer contexts.
Multi-Review Fusion-in-Context (2024.findings-naacl)

Copied to clipboard

Challenge: Current methods for generating text are opaque and difficult to control and interpret due to their opaque nature.
Approach: They propose a modular approach with separate components for each step . they formalize Fusion-in-Context as a standalone task, whose input consists of source texts with highlighted spans of targeted content.
Outcome: The proposed approach is based on a curated dataset of 1000 instances in the reviews domain and a novel evaluation framework for assessing the faithfulness and coverage of highlights.
The Power of Summary-Source Alignments (2024.findings-acl)

Copied to clipboard

Challenge: Multi-document summarization (MDS) is a challenging task, often decomposed to subtasks of salience and redundancy detection, followed by text generation.
Approach: They propose to extend the summary-source alignment framework by applying it at the more fine-grained proposition span level and annotating alignment manually in a multi-document setup.
Outcome: The proposed framework can yield several datasets for at least six different tasks.
Attribute First, then Generate: Locally-attributable Grounded Text Generation (2024.acl-long)

Copied to clipboard

Challenge: Recent efforts to address hallucinations in Large Language Models have focused on attributed text generation, which supplements generated texts with citations of supporting sources for post-generation fact-checking and corrections.
Approach: They propose a locally-attributable text generation approach prioritizing concise attributions by identifying relevant source segments and conditioning the generation process on them.
Outcome: The proposed method yields more concise citations than baselines and significantly reduces time required for fact verification by human assessors.
RefVNLI: Towards Scalable Evaluation of Subject-driven Text-to-image Generation (2025.findings-emnlp)

Copied to clipboard

Challenge: Existing methods assess only one aspect of the task, misalign with human judgments or rely on costly API-based evaluation.
Approach: RefVNLI evaluates textual alignment and subject preservation in a single run.
Outcome: RefVNLI outperforms or matches existing baselines across multiple benchmarks and subject categories.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations