Papers by Dilek Hakkani-Tur

22 papers
Aligning LLMs with Individual Preferences via Interaction (2025.coling-main)

Copied to clipboard

Challenge: Existing studies on LLMs alignment focus on generalizing their behavior to generalized values such as helpfulness, harmlessness, and honesty.
Approach: They train large language models to "interact to align" to implicitly infer user preferences . they use a multi-turn preference dataset to generate a personalized alignment .
Outcome: The proposed method enables dynamic, personalized alignment via interaction with a multi-turn preference dataset.
Few Shot Dialogue State Tracking using Meta-learning (2021.eacl-main)

Copied to clipboard

Challenge: Existing methods for transferring knowledge from resource-rich domains to unknown domains are data hungry . a meta-learning algorithm is proposed to solve the problem of zero/few-shot DST .
Approach: They propose a meta-learner for the problem of zero/few-shot DST . they propose to agnostically train any existing chatbot system to improve its performance .
Outcome: The proposed meta-learner improves on baseline in a low-data setting.
What is wrong with you?: Leveraging User Sentiment for Automatic Dialog Evaluation (2022.findings-acl)

Copied to clipboard

Challenge: Existing metrics for dialog evaluation are trained on human annotations, which is cumbersome to collect.
Approach: They propose to use user sentiment and other information as proxy to measure the quality of previous dialogs.
Outcome: The proposed model is comparable to models trained on human annotated data.
ALFRED-L: Investigating the Role of Language for Action Learning in Interactive Visual Environments (2022.emnlp-main)

Copied to clipboard

Challenge: Embodied Vision and Language Task Completion requires an embodied agent to interpret natural language instructions and egocentric visual observations to navigate through and interact with environments.
Approach: They propose to use ALFRED to test whether models can adapt to tasks not seen during training that require the same types of language understanding as ALFred.
Outcome: The proposed model can adapt to tasks that require the same types of language understanding as ALFRED-L.
DialGuide: Aligning Dialogue Model Behavior with Developer Guidelines (2023.findings-emnlp)

Copied to clipboard

Challenge: Dialogue models are able to generate fluent and interesting responses, but they can be difficult to control and may produce non-engaging, unsafe results.
Approach: They propose a framework for controlling dialogue model behavior using natural language rules, or guidelines, which provide information about the context they are applicable to and what should be included in the response.
Outcome: The proposed framework is effective in three open-domain dialogue response generation tasks and is consistent with the developer's expectations and intent.
Alexa Conversations: An Extensible Data-driven Approach for Building Task-oriented Dialogue Systems (2021.naacl-demos)

Copied to clipboard

Challenge: Traditional goal-oriented dialogue systems require annotations which are hard to obtain for every new domain, limiting scalability.
Approach: They propose a data-driven approach to building goal-oriented dialogue systems . they use a seed dialogue simulator to generate annotated conversations instead of collecting annotations .
Outcome: The proposed system improves turn-level action signature prediction accuracy by 50% . the system is scalable, extensible and data efficient .
PLACES: Prompting Language Models for Social Conversation Synthesis (2023.findings-eacl)

Copied to clipboard

Challenge: Currently, collecting high quality conversational data is expensive and infeasible for many applications . a promising direction is to generate synthetic dialogues by prompting large language models .
Approach: They propose to use expert-written conversations as in-context examples to generate synthetic dialogues by prompting large language models.
Outcome: The proposed approach is generalizable to multi-party conversations, compared to human-collected conversations.
MultiWOZ 2.1: A Consolidated Multi-Domain Dialogue Dataset with State Corrections and State Tracking Baselines (2020.lrec-1)

Copied to clipboard

Challenge: MultiWOZ 2.0 has substantial noise in dialogue state annotations and dialogue utterances . follow-up work has augmented the original dataset with user dialogue acts .
Approach: They propose to reannotate dialogue state and utterances based on original dataset . they then compare their results to other datasets to improve their models .
Outcome: The proposed dataset improves on the noise in the dialogue state annotations and dialogue utterances.
Robust Zero-Shot Cross-Domain Slot Filling with Example Values (P19-1)

Copied to clipboard

Challenge: Task-oriented dialog systems rely on deep learning-based slot filling models . little to no training data for target domains may be available or schemas may not be aligned .
Approach: They propose to use slot descriptions and examples of slot values to learn slot semantic representations that are transferable across domains and robust to misaligned schemas.
Outcome: The proposed model outperforms state-of-the-art models on two multi-domain datasets on low-data setting.
Inducer-tuning: Connecting Prefix-tuning and Adapter-tuning (2022.emnlp-main)

Copied to clipboard

Challenge: Prefix-tuning is an essential paradigm of parameter-efficient transfer learning . fine-tuned models require separate copies of model parameters for each task .
Approach: They propose to understand and further develop prefix-tuning through the kernel lens . they propose a new variant of prefix tuning that shares the exact mechanism as prefix tun .
Outcome: The proposed method improves prefix-tuning performance by training only a small portion of parameters.
Analyzing the Limits of Self-Supervision in Handling Bias in Language (2022.findings-emnlp)

Copied to clipboard

Challenge: a recent study shows that natural language models can perform tasks with little to no in-context supervision . a number of tasks are performed using self-supervised pre-training .
Approach: They define and comprehensively evaluate how well natural language taskprompting captures the semantics of four tasks for bias: diagnosis, identification, extraction and rephrasing.
Outcome: The proposed model performs to wide varying degrees across bias dimensions . the model is largely challenged when prompted to perform these tasks .
Multimodal Embodied Plan Prediction Augmented with Synthetic Embodied Dialogue (2023.emnlp-main)

Copied to clipboard

Challenge: Embodied task completion requires an agent to predict environment actions to complete tasks based on natural language instructions and egocentric visual observations.
Approach: They propose a method to generate human-human dialogues and use them as training data for plan prediction.
Outcome: The proposed model outperforms language-only models but falls short of oracle plans.
Think Before You Speak: Explicitly Generating Implicit Commonsense Knowledge for Response Generation (2022.acl-long)

Copied to clipboard

Challenge: Current neural response generation models generate responses directly, omitting unstated implicit knowledge.
Approach: They propose a generative approach to externalize implicit commonsense knowledge and use it to generate responses.
Outcome: Empirical results show that TBS models outperform end-to-end RG models on most automatic metrics and generate more informative, specific, and commonsense-following responses.
Empowering parameter-efficient transfer learning by recognizing the kernel structure in self-attention (2022.findings-naacl)

Copied to clipboard

Challenge: Existing methods to fine-tune pre-trained language models are parameter efficient . fine- tuning the models requires multiple copies of the parameters, which is inefficient.
Approach: They propose to use kernel-based adapters to tune only a few parameters while freezing the rest of the parameters.
Outcome: The proposed methods achieve or improve strong performance over a diverse set of natural language generation and understanding tasks.
Using In-Context Learning to Improve Dialogue Safety (2023.findings-emnlp)

Copied to clipboard

Challenge: Recent work has highlighted safety issues with large neural-based conversational models.
Approach: They propose a retrieval-based approach for reducing bias and toxicity in chatbot responses . they retrieve demonstrations of safe responses to similar dialogue contexts to generate a response .
Outcome: The proposed method reduces bias and toxicity in three chatbot models . it can be used in compliment to existing dialogue safety approaches, such as RLHF.
Sketching as a Tool for Understanding and Accelerating Self-attention for Long Sequences (2022.naacl-main)

Copied to clipboard

Challenge: Existing models for long sequences are not efficient due to the quadratic space and time complexity of the self-attention modules.
Approach: They propose to reduce the quadratic complexity to linear (modulo logarithmic factors) by low-dimensional projection and row selection.
Outcome: The proposed methods outperform transformer-based models with smaller time/space footprint on the Long Range Arena benchmark.
Entity Resolution in Open-domain Conversations (2021.naacl-industry)

Copied to clipboard

Challenge: Recent work on incorporating external knowledge into the response generation models has attracted great interest.
Approach: They propose a neural entity linking approach to incorporate external knowledge into the response generation models to improve the relevancy of retrieved knowledge.
Outcome: The proposed approach outperforms the baseline model by 62.8% relative to the baseline.
Selective In-Context Data Augmentation for Intent Detection using Pointwise V-Information (2023.eacl-main)

Copied to clipboard

Challenge: Intent detection is a fundamental element in task-oriented dialogue systems, usually occurring within the Natural Language Understanding component.
Approach: They propose an in-context data augmentation approach that fine-tunes a pre-trained language model and synthesizes new datapoints that correspond to given intents.
Outcome: The proposed method produces training data that achieves state-of-the-art on three challenging intent detection datasets and performs on par with the state- of-the art in full-shot settings.
Enhancing Knowledge Selection for Grounded Dialogues via Document Semantic Graphs (2022.naacl-main)

Copied to clipboard

Challenge: Existing conversation models treat knowledge selection as a sentence ranking problem where each sentence is handled individually, ignoring the internal semantic connection between sentences.
Approach: They propose to automatically convert background knowledge documents into document semantic graphs and perform knowledge selection over such graphs.
Outcome: The proposed model improves on the knowledge selection task and the response generation task on HollE and generalizes on unseen topics in WoW.
KILM: Knowledge Injection into Encoder-Decoder Language Models (2023.acl-long)

Copied to clipboard

Challenge: Large pre-trained language models retain implicit knowledge within their parameters, but are susceptible to memorizing the pretraining corpora rather than capturing the knowledge within them.
Approach: They propose to inject entity-related knowledge into encoder-decoder PLMs via a generative knowledge infilling objective through continued pre-training.
Outcome: The proposed approach outperforms state-of-the-art models on general NLU and NLG tasks while maintaining their original performance.
VISITRON: Visual Semantics-Aligned Interactively Trained Object-Navigator (2022.findings-acl)

Copied to clipboard

Challenge: Interactive robots navigating photo-realistic environments need to be trained to handle dynamic nature of dialogue and vision-and-language navigation (VLN).
Approach: They propose a Transformer-based multi-modal navigator that is better suited to the interactive regime inherent to Cooperative Vision-and-Dialog Navigation (CVDN).
Outcome: The proposed model is trained to identify and associate object-level concepts and semantics between the environment and dialogue history and identify when to interact vs. navigate via imitation learning of a binary classification head.
CESAR: Automatic Induction of Compositional Instructions for Multi-turn Dialogs (2023.emnlp-main)

Copied to clipboard

Challenge: Instruction-based multitasking has played a critical role in the success of large language models (LLMs) when exposed to complex instructions with multiple constraints, they lag against state-of-the-art models like ChatGPT.
Approach: They propose a framework that unifies a large number of dialog tasks in the same format and allows programmatic induction of complex instructions without manual effort.
Outcome: The proposed framework unifies a large number of dialog tasks in the same format and allows programmatic induction of complex instructions without manual effort.

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