Natural Language Processing

Materials of transformers lecture course

Detecting overflow in compressed token representations for RAG

No description provided.

Ridic

[ACL 2025] Adaptive Retrieval without Self-Knowledge? Bringing Uncertainty Back Home

No description provided.

Models for automatically transforming toxic text to neutral

http://nlp.seas.harvard.edu/2018/04/03/attention.html

Code and data of "Methods for Detoxification of Texts for the Russian Language" paper

No description provided.

ConflictBench

No description provided.

This repository provides the code implementation for the paper: "Memory Efficient LM Compression using Fisher Information from Low-Rank Representations"

No description provided.

The PsiloQA pipeline automates the construction of a multilingual, span-level hallucination detection dataset with contexts.

Official implementation of NAACL 2025 SRW paper "SkipCLM: Enhancing Crosslingual Alignment of Decoder Transformer Models via Contrastive Learning and Skip Connection"

Data and info for the paper "ParaDetox: Text Detoxification with Parallel Data"

SHROOM SemEval shared task code and data

Project on transformers compression

RUSSE 2022: Russian Text Detoxification Based on Parallel Corpora

No description provided.

No description provided.

No description provided.

The code related to the paper

Official implementation of NAACL 2025 Main Conference Paper "Modern LLMs are Few-Shot Parallel Detoxification Data Annotators"

Through the Looking Glass

No description provided.

Data from "Crowdsourcing of Parallel Corpora: the Case of Style Transfer for Detoxification" paper

A code for PAN-2024 Multilingual Text Detoxification

Dataset for evaluating the quality of content preservation measure in text formality transfer for task oriented domain