Papers by Harsh Jhamtani

20 papers
Towards Robust Evaluation of Unlearning in LLMs via Data Transformations (2024.findings-emnlp)

Copied to clipboard

Challenge: Large Language Models (LLMs) have shown to be a great success in a wide range of applications ranging from regular NLP-based use cases to AI agents.
Approach: They examine the robustness of existing MUL techniques for their ability to enable leakage-proof forgetting in LLMs.
Outcome: The proposed methods can be used to enable leakage-proof forgetting in LLMs.
Learning Rhyming Constraints using Structured Adversaries (D19-1)

Copied to clipboard

Challenge: Existing approaches to text generation fail to capture higher-level structure in text, for example, rhyming patterns.
Approach: They propose a method that uses a structured discriminator to learn rhyming constraints from poetry . the discriminator compares two English poetry datasets based on a learned similarity matrix .
Outcome: The proposed method can learn rhyming patterns in English poetry without explicit phonetic information.
Language-to-Code Translation with a Single Labeled Example (2024.emnlp-main)

Copied to clipboard

Challenge: In-Context Inverse Programming (ICIP) bootstraps a language-to-code system using mostly unlabeled programs written using a potentially unfamiliar library or API.
Approach: They propose a method for bootstrapping a language-to-code system using mostly unlabeled programs written using a potentially unfamiliar library or API.
Outcome: The proposed method outperforms baselines across nine domains and 100 examples in a “nearly unsupervised” setting.
Learning to Generate Move-by-Move Commentary for Chess Games from Large-Scale Social Forum Data (P18-1)

Copied to clipboard

Challenge: Using a large-scale chess commentary dataset, we generate a set of comments for individual moves in a game.
Approach: They propose a large-scale chess commentary dataset and a method to generate commentary for individual moves in a chessian game.
Outcome: The proposed method is rated similar to ground truth commentary texts in terms of correctness and fluency.
The Whole Truth and Nothing But the Truth: Faithful and Controllable Dialogue Response Generation with Dataflow Transduction and Constrained Decoding (2023.findings-acl)

Copied to clipboard

Challenge: In a task-oriented dialogue system, response generation is a conditional language model, but effective dialogue agents must balance fluent generation with stricter constraints.
Approach: They propose a rule-based content selection model that transduces a dialogue agent’s actions and their results into context-free grammars representing the space of contextually acceptable responses.
Outcome: The proposed architecture outperforms both rule-based and learned approaches in human evaluations of fluency, relevance, and truthfulness.
Interpreting User Requests in the Context of Natural Language Standing Instructions (2024.findings-naacl)

Copied to clipboard

Challenge: Existing approaches to LLM-based dialogue modeling provide additional context for users to make requests.
Approach: They propose an approach to LLM-based dialogue modeling where persistent user constraints and preferences are provided as additional context for such interfaces.
Outcome: The proposed model achieves a maximum of 46% exact match on the prediction of 2.4K English dialogues with a language-to-program dataset.
LLM Agents for Coordinating Multi-User Information Gathering (2025.findings-acl)

Copied to clipboard

Challenge: Recent large language models (LLMs) are becoming a crucial building block in developing automated agents that can assist human users with complex tasks.
Approach: They introduce PeopleJoin, a benchmark for evaluating LM-mediated collaborative problem solving.
Outcome: The proposed benchmarks are adapted from existing benchmarks for database question answering and multi-document summarization.
Target-Guided Dialogue Response Generation Using Commonsense and Data Augmentation (2022.findings-naacl)

Copied to clipboard

Challenge: Existing methods for target-guided response generation are inconsistent with human judgement ratings.
Approach: They propose a technique that finds a bridging path between the source and target and uses it to generate transition responses.
Outcome: The proposed technique outperforms baselines on target-guided response generation task.
Improving Automated Evaluation of Open Domain Dialog via Diverse Reference Augmentation (2021.findings-acl)

Copied to clipboard

Challenge: Prior work has shown that having multiple valid references is important for automated evaluations.
Approach: They propose a technique for automatically expanding a human generated reference to a set of candidate references.
Outcome: The proposed method improves correlations between human-generated metrics and human ratings of system outputs.
Narrative Text Generation with a Latent Discrete Plan (2020.findings-emnlp)

Copied to clipboard

Challenge: Prior work on story generation has focused on generating consistent stories via story outlines using keywords or key phrases.
Approach: They propose a deep latent variable model that first samples a sequence of anchor words, one per sentence in the story, as part of its generative process.
Outcome: The proposed model gets favorable scores when evaluated on perplexity, diversity, and control of story via discrete plan.
Unsupervised Enrichment of Persona-grounded Dialog with Background Stories (2021.acl-short)

Copied to clipboard

Challenge: Existing dialog models do not contain such narratives, so we propose a gradient-based rewriting technique to enrich dialog personas with relevant background events.
Approach: They propose to use existing dialog datasets to enrich dialog responses with 'background stories' based on a gradient-based rewriting technique which encourages the generated response to be fluent with the dialog history, minimally different from the retrieved story, and consistent with the original persona.
Outcome: The proposed method generates responses that are more diverse and human-like compared to outputs from existing dialog models.
Learning to Explain: Datasets and Models for Identifying Valid Reasoning Chains in Multihop Question-Answering (2020.emnlp-main)

Copied to clipboard

Challenge: despite rapid progress in multihop question-answering, models still have trouble explaining why an answer is correct.
Approach: They propose three explanation datasets in which explanations from corpus facts are annotated . they first annotate multiple candidate explanations for each answer, then use crowd-sourcing perturbations to test generalization .
Outcome: The proposed datasets improve explanation quality but still behind the upper bound . the proposed dataset can be used to improve explanations using a BERT-based classifier .
Learning to Retrieve Iteratively for In-Context Learning (2024.emnlp-main)

Copied to clipboard

Challenge: In-context learning is a powerful tool for learning large language models.
Approach: They propose an iterative retrieval framework that empowers retrievers to make iterable decisions through policy optimization.
Outcome: The proposed framework outperforms existing methods on semantic parsing datasets with 4M additional parameters for state encoding.
PINEAPPLE: Personifying INanimate Entities by Acquiring Parallel Personification Data for Learning Enhanced Generation (2022.coling-1)

Copied to clipboard

Challenge: Personifications are figures of speech that endow inanimate entities with properties and actions typically seen as requiring animacy.
Approach: They propose to use personification data to train a parallel corpus of personifications . they propose to combine personification-related literalizations with automatic ones .
Outcome: The proposed personification system can generate diverse and creative personifications . it can generate personification-related qualities such as interestingness and animacy .
Ontologically Faithful Generation of Non-Player Character Dialogues (2024.emnlp-main)

Copied to clipboard

Challenge: a key challenge in creating NPC dialogues is that they should serve coherent narratives.
Approach: They propose to use supervised and in-context learning techniques to generate trees of dialogue between video game characters that accurately reflect quest and entity specifications.
Outcome: The proposed model performs well but room for improvement.
Truth-Conditional Captions for Time Series Data (2021.emnlp-main)

Copied to clipboard

Challenge: Existing models with attention mechanisms can generate fluent descriptions of salient patterns in time series, but they often generate factually incorrect descriptions.
Approach: They propose a model which first runs small learned programs on the input time series, then identifies the programs/patterns which hold true for the given input, and finally conditions on *only* the chosen valid program to generate the output text description.
Outcome: The proposed model extracts high-level patterns from the data and generates high precision captions even though it is built on a small space of modules.
Like hiking? You probably enjoy nature: Persona-grounded Dialog with Commonsense Expansions (2020.emnlp-main)

Copied to clipboard

Challenge: Existing persona-grounded dialog models fail to capture simple implications of given persona descriptions.
Approach: They propose to expand available persona sentences using existing commonsense knowledge bases and paraphrasing resources to imbue dialog models with access to expanded and richer set of persona descriptions.
Outcome: The proposed model outperforms baselines on the Persona-Chat dataset in terms of dialog quality and diversity while achieving persona-consistent and controllable dialog generation.
Achieving Conversational Goals with Unsupervised Post-hoc Knowledge Injection (2022.acl-long)

Copied to clipboard

Challenge: Existing neural dialog models lack specificity and informativeness due to limited knowledge available during training.
Approach: They propose a method to extract relevant knowledge from external sources at decoding time and incorporate it into a dialog response.
Outcome: The proposed method in goal-oriented and knowledge-grounded dialog settings shows that human annotators judge the outputs more engaging and informative compared to responses from prior dialog systems.
Investigating Robustness of Dialog Models to Popular Figurative Language Constructs (2021.emnlp-main)

Copied to clipboard

Challenge: Existing dialog models are unable to handle popular figurative language constructs like metaphor and simile when faced with dialog contexts containing figurativ language.
Approach: They propose lightweight solutions to help existing dialog models become more robust to figurative language by simply using an external resource to translate figurativ language to literal (non-figurative) forms while preserving the meaning to the best extent possible.
Outcome: The proposed models show large drops in performance when faced with dialog contexts consisting of figurative language compared to contexts without figurativ language .
Learning to Describe Differences Between Pairs of Similar Images (D18-1)

Copied to clipboard

Challenge: Using crowd-sourced annotations, we generate text descriptions of differences between two images . we use a dataset to generate concise and fluent descriptions of visual data .
Approach: They propose a task of automatically generating text to describe the differences between two images . they crowd-sourced the difference descriptions for pairs of images extracted from video-surveillance footage .
Outcome: The proposed model outperforms models that use attention alone for single-sentence generation and multi-sentent generation.

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