Papers by Richard Zemel

12 papers
Training-free Deep Concept Injection Enables Language Models for Video Question Answering (2024.emnlp-main)

Copied to clipboard

Challenge: Existing methods to train pretrained language models for zero-shot crossmodal tasks require crossmodal pretraining.
Approach: They propose to inject visual concepts into the input text embedding space of a pretrained language model and build adaptation layers based on the intermediate representation of concepts.
Outcome: The proposed model performs zero-shot crossmodal tasks without crossmodal pretraining . it is based on the injection of visual concepts as input tokens and augmentation in intermediate features . the proposed model achieves competitive or even better results in zero- shot and fine-tuning settings .
Whiteboard-of-Thought: Thinking Step-by-Step Across Modalities (2024.emnlp-main)

Copied to clipboard

Challenge: Large language models have shown promising results in arithmetic and symbolic reasoning by expressing intermediate reasoning in text as a chain of thought, yet struggle to extend this capability to answer text queries that are easily solved by visual reasoning.
Approach: They propose a method to unlock the visual reasoning capabilities of multimodal large language models by using a metaphorical ‘whiteboard’ to draw out reasoning steps as images and return these images back to the model for further processing.
Outcome: The proposed method shows that it can be used on four difficult tasks that involve visual and spatial reasoning with no demonstrations or specialized modules.
Coordinated Replay Sample Selection for Continual Federated Learning (2023.emnlp-industry)

Copied to clipboard

Challenge: Continual Federated Learning (CFL) combines decentralized learning with continuous learning . ubiquity of personal devices with a network connection offers rich source of data for learning problems .
Approach: They propose to combine decentralized learning with a continuous learning approach . they propose to coordinate gradient-based replay sample selection across clients .
Outcome: The proposed method shows gains early in the low replay size regime, when the budget for storing past data is small.
A Computational Framework for Slang Generation (2021.tacl-1)

Copied to clipboard

Challenge: Existing language models trained on large text corpora are biased toward formal language and under-represent slang.
Approach: They propose a framework that models the speaker’s word choice in slang context by relating the conventional and sexist senses of a word while incorporating syntactic and contextual knowledge.
Outcome: The proposed framework outperforms state-of-the-art language models and better predicts the historical emergence of slang word usages from 1960s to 2000s.
The steerability of large language models toward data-driven personas (2024.naacl-long)

Copied to clipboard

Challenge: Large language models generate biased responses where opinions of certain groups and populations are underrepresented.
Approach: They propose a data-driven notion of persona that allows for a more nuanced understanding of different (latent) social groups present in the population.
Outcome: The proposed method improves model steerability by 57% over baselines.
Attribute Controlled Fine-tuning for Large Language Models: A Case Study on Detoxification (2024.findings-emnlp)

Copied to clipboard

Challenge: Using a sequence-level constraint, we regularize the LLMtraining by penalizing the KL divergence between the desired output distribution and the LRM’s posterior.
Approach: They propose a constraint learning schema forfine-tuning Large Language Models with attribute control by penalizing the KL divergence be-tween the desired output distribution and the LLM's posterior.
Outcome: The proposed approach improves the performance of large language models while enhancing their utility and generation quality.
FLIRT: Feedback Loop In-context Red Teaming (2024.emnlp-main)

Copied to clipboard

Challenge: Recent work has evaluated the vulnerabilities of large generative models, such as DALL-E, ChatGPT, and GPT-4.
Approach: They propose an automatic red teaming framework that evaluates a given black-box model and exposes its vulnerabilities against unsafe and inappropriate content generation.
Outcome: The proposed framework evaluates a given black-box model and exposes its vulnerabilities against unsafe and inappropriate content generation.
Tokenization Matters: Navigating Data-Scarce Tokenization for Gender Inclusive Language Technologies (2024.findings-naacl)

Copied to clipboard

Challenge: a recent study documented the harmful limitations of gender binary-centric large language models . data scarcity is a known culprit, but the precise mechanisms through which scarcity affects this behavior remain underexplored.
Approach: They propose to use BPE tokenization to enforce consistent tokenization across gendered pronouns to improve neopronoun proficiency.
Outcome: The proposed methods outperform finetuning with standard BPE, and improve neopronoun proficiency.
Toward Informal Language Processing: Knowledge of Slang in Large Language Models (2024.naacl-long)

Copied to clipboard

Challenge: Recent advances in large language models (LLMs) have offered a strong potential for natural language systems to process informal language.
Approach: They propose to use movie subtitles to evaluate slang in large language models . they find that smaller LLMs finetuned on the dataset achieve comparable performance .
Outcome: The proposed dataset can be used to evaluate LLMs on slang detection and identification of regional and historical sources for interpretive insights.
Semantically Informed Slang Interpretation (2022.naacl-main)

Copied to clipboard

Challenge: Existing approaches to slang interpretation rely on context but ignore semantic extensions common in slings . a semantically informed slapping framework can be applied to enhancing machine translation of informal language .
Approach: They propose a semantically informed slang interpretation framework that considers contextual and semantic appropriateness of a candidate interpretation for a query s.
Outcome: The proposed framework achieves state-of-the-art accuracy in slang interpretation in English and in other languages.
Resolving Ambiguities in Text-to-Image Generative Models (2023.acl-long)

Copied to clipboard

Challenge: ambiguities can lead to misinterpretation and miscommunication in natural language . resolving ambiguity is notoriously hard for machines .
Approach: They propose a framework to disambiguate prompts given to generative models by soliciting clarifications from the end user.
Outcome: The proposed framework generates more faithful images better aligned with user intention in the presence of ambiguities.
Towards Safety Reasoning in LLMs: AI-agentic Deliberation for Policy-embedded CoT Data Creation (2025.findings-acl)

Copied to clipboard

Challenge: Safety reasoning paradigms require high-quality policy-embedded chain-of-thought datasets . generating such data through human annotations is prohibitively expensive .
Approach: They propose AIDSAFE: Agentic Iterative Deliberation for Safety Reasoning . AIDS AFE leverages multi-agent deliberation to iteratively expand reasoning on safety policies .
Outcome: The proposed model improves policy adherence and reasoning quality while maintaining acceptable utility and over-refusal accuracy.

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