Papers by Shikib Mehri
“None of the Above”: Measure Uncertainty in Dialog Response Retrieval (2020.acl-main)
Copied to clipboard
| Challenge: | End-to-end (E2E) dialog retrieval models jointly encode a dialog and a candidate response, assuming the ground truth is always present in the candidate set. |
| Approach: | They propose to capture the original retrieval model's confidence concerning the best prediction using trivial additional computation. |
| Outcome: | The proposed model can capture the model's confidence concerning the best prediction using trivial additional computation. |
USR: An Unsupervised and Reference Free Evaluation Metric for Dialog Generation (2020.acl-main)
Copied to clipboard
| Challenge: | Standard language generation metrics have been shown to be ineffective for dialog evaluation. |
| Approach: | They propose an unsupervised evaluation metric for dialog that trains unsupervised models to measure several desirable qualities of dialog. |
| Outcome: | The proposed evaluation metric strongly correlates with human judgment on Topical-Chat and PersonaChat. |
Multi-Granularity Representations of Dialog (D19-1)
Copied to clipboard
| Challenge: | Neural models of dialog rely on generalized latent representations of language. |
| Approach: | They propose a training procedure which explicitly learns multiple representations of language at several levels of granularity. |
| Outcome: | The proposed training procedure significantly improves performance on the next utterance retrieval task using the MultiWOZ dataset and the Ubuntu dialog corpus. |
Pretraining Methods for Dialog Context Representation Learning (P19-1)
Copied to clipboard
| Challenge: | Existing methods for pretraining dialog context encoders are still in their infancy. |
| Approach: | They propose to use unsupervised pretraining objectives for dialog context representations to fine-tune and evaluate them on a set of downstream dialog tasks. |
| Outcome: | The proposed methods improve performance on a set of dialog tasks and are less data hungry. |
Interactive Evaluation of Dialog Track at DSTC9 (2022.lrec-1)
Copied to clipboard
| Challenge: | Currently, dialog research is focused on static data, which neglects multiple important properties of dialog, such as consistency, topic depth, adaptation, error recovery and user-centric development. |
| Approach: | They propose to use static dialogs to build strong response generation models and extend them to back-and-forth interactions with real users. |
| Outcome: | The proposed model trains a larger evolved Transformer model on social media data and attains strong performance in interactive settings. |
LMUNIT: Fine-grained Evaluation with Natural Language Unit Tests (2025.findings-emnlp)
Copied to clipboard
Jon Saad-Falcon, Rajan Pathe Vivek, William Berrios, Nandita Shankar Naik, Matija Franklin, Bertie Vidgen, Amanpreet Singh, Douwe Kiela, Shikib Mehri
| Challenge: | Using natural language unit tests, language models are costly and noisy, and automated metrics provide only coarse, difficult-to-interpret signals. |
| Approach: | They propose a paradigm that decomposes response quality into explicit, testable criteria and a unified scoring model, LMUnit, which combines multi-objective training across preferences, direct ratings, and natural language rationales. |
| Outcome: | The proposed paradigm significantly improves inter-annotator agreement and enables more effective LLM development workflows. |
Example-Driven Intent Prediction with Observers (2021.naacl-main)
Copied to clipboard
| Challenge: | Prior work has shown that BERT-like models attribute a significant amount of attention to the [CLS] token, which results in diluted representations. |
| Approach: | They propose two approaches to improve generalizability of dialog system intent classification models by using observers and example-driven training. |
| Outcome: | The proposed models achieve state-of-the-art on three intent prediction datasets in both the full data and few-shot settings. |
InstructDial: Improving Zero and Few-shot Generalization in Dialogue through Instruction Tuning (2022.emnlp-main)
Copied to clipboard
| Challenge: | Instruction tuning is emerging in NLP, but has not been explored for dialogue-related tasks. |
| Approach: | They propose an instruction tuning framework for dialogue that leverages natural language instructions with language models to induce zero-shot generalization on unseen tasks. |
| Outcome: | The proposed framework enables good zero-shot performance on unseen datasets and tasks such as dialogue evaluation and intent detection. |
CESAR: Automatic Induction of Compositional Instructions for Multi-turn Dialogs (2023.emnlp-main)
Copied to clipboard
Taha Aksu, Devamanyu Hazarika, Shikib Mehri, Seokhwan Kim, Dilek Hakkani-Tur, Yang Liu, Mahdi Namazifar
| 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. |