Papers by Gal Chechik
Multilingual word translation using auxiliary languages (D19-1)
Copied to clipboard
| Challenge: | Existing multilingual word translation methods focus on learning mappings from each language to a shared space. |
| Approach: | They propose a multilingual translation procedure that uses all the learned mappings to translate a word from one language to another. |
| Outcome: | Experiments on a standard multilingual word translation benchmark show that the proposed translation procedure outperforms state-of-the-art translation methods. |
Knowing Before Saying: LLM Representations Encode Information About Chain-of-Thought Success Before Completion (2025.findings-acl)
Copied to clipboard
| Challenge: | Using later reasoning steps does not always improve classification, suggesting LLMs encode key information early. |
| Approach: | They propose a method to predict the success of a zero-shot Chain-of-Thought process by using LLM representations that are based on initial steps representations. |
| Outcome: | The proposed method performs well even before a single token is generated, suggesting that crucial information about the reasoning process is already present in the initial steps representations. |
A Multi-Pairwise Extension of Procrustes Analysis for Multilingual Word Translation (D19-1)
Copied to clipboard
| Challenge: | Existing approaches to multilingual word embeddings require a k-way dictionary. |
| Approach: | They propose a novel approach to simultaneously representing multiple languages in a common space by using a pairwise bilingual dictionary. |
| Outcome: | The proposed approach requires only pairwise bilingual dictionaries that are much easier to construct. |
LR-DWM: Efficient Watermarking for Diffusion Language Models (2026.findings-acl)
Copied to clipboard
| Challenge: | Current methods for large language models rely on tokens being generated sequentially . left-right Diffusion watermarking uses a fixed, deterministic left-to-right order . |
| Approach: | They propose a scheme that biases tokens based on both left and right neighbors . left-Right Diffusion Watermarking is a low-latency alternative to autoregressive models . |
| Outcome: | The proposed method can be watermarked efficiently with minimal runtime and memory overhead. |
Text2Model: Text-based Model Induction for Zero-shot Image Classification (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Existing approaches to zero-shot learning are limited in two ways: Query-dependence and richness of language description. |
| Approach: | They propose a task-agnostic approach to image classification using only text descriptions . they train a hypernetwork that receives class descriptions and outputs a multi-class model . |
| Outcome: | The proposed approach generates non-linear classifiers, handles rich textual descriptions, and may be adapted to produce lightweight models efficient enough for on-device applications. |
Example-based Hypernetworks for Multi-source Adaptation to Unseen Domains (2023.findings-emnlp)
Copied to clipboard
| Challenge: | In order to achieve unprecedented performance, many out-of-distribution generalization approaches use unlabeled data from the target distribution. |
| Approach: | They propose a framework that leverages labeled data from multiple source domains to generalize to unknown target domains at training. |
| Outcome: | The proposed framework outperforms existing models in two tasks, and it is compared to few-shot GPT-3. |
ZEST: Zero-shot Learning from Text Descriptions using Textual Similarity and Visual Summarization (2020.findings-emnlp)
Copied to clipboard
| Challenge: | Specifically, given birds’ images with free-text descriptions of their species, we learn to classify images of previously-unseen species based on specie descriptions. |
| Approach: | They propose to leverage the similarity between species and extract visual summaries from the texts to match visual features to the parts of the text that discuss them. |
| Outcome: | The proposed model outperforms the state-of-the-art on the largest benchmarks for text-based zero-shot learning. |
Padding Tone: A Mechanistic Analysis of Padding Tokens in T2I Models (2025.naacl-long)
Copied to clipboard
| Challenge: | Text-to-image (T2I) diffusion models rely on encoded prompts to guide the image generation process. |
| Approach: | They conduct the first in-depth analysis of the role padding tokens play in T2I diffusion models by using two causal techniques to analyze how information is encoded in the representation of tokens across different components of the pipeline. |
| Outcome: | The proposed techniques reveal that padding tokens may affect the model’s output during text encoding, during the diffusion process, or be effectively ignored. |