Papers by Or Honovich
Unnatural Instructions: Tuning Language Models with (Almost) No Human Labor (2023.acl-long)
Copied to clipboard
| Challenge: | Instruction tuning enables pretrained language models to perform new tasks from inference-time natural language descriptions without human supervision. |
| Approach: | They propose to use a dataset of natural language instructions to generate large datasets with no human supervision. |
| Outcome: | The proposed dataset outperforms open-source models on various benchmarks, and is cost-effective. |
DisentQA: Disentangling Parametric and Contextual Knowledge with Counterfactual Question Answering (2023.acl-long)
Copied to clipboard
| Challenge: | Question answering models have access to two sources of knowledge during inference time: parametric knowledge and contextual knowledge. |
| Approach: | They propose a new paradigm in which QA models are trained to disentangle the two sources of knowledge. |
| Outcome: | The proposed model generates two answers for a given question based on parametric and contextual knowledge. |
Q2: Evaluating Factual Consistency in Knowledge-Grounded Dialogues via Question Generation and Question Answering (2021.emnlp-main)
Copied to clipboard
| Challenge: | Existing evaluation methods for factual consistency in knowledge-grounded dialogues are unreliable and limit their applicability. |
| Approach: | They propose an automatic evaluation metric for factual consistency in knowledge-grounded dialogue using automatic question generation and question answering. |
| Outcome: | The proposed evaluation metric consistently shows higher correlation with human judgements. |
LMentry: A Language Model Benchmark of Elementary Language Tasks (2023.findings-acl)
Copied to clipboard
| Challenge: | Large language models are evaluated via perplexity or performance on downstream tasks, but these benchmarks are too complex and difficult to inspect. |
| Approach: | They propose a benchmark that focuses on 25 tasks that humans are expected to perform perfectly, such as writing a sentence containing a specific word or identifying which words in a list belong to a certain category. |
| Outcome: | The proposed benchmarks show that large language models are performing better than previous benchmarks. |
Instruction Induction: From Few Examples to Natural Language Task Descriptions (2023.acl-long)
Copied to clipboard
| Challenge: | Large language models can perform unseen tasks by conditioning on a few input-output demonstrations, but task inference is implicit and the ability of models to explicitly reason about it remains unexplored. |
| Approach: | They propose an instruction induction challenge in which a model is asked to generate a natural language instruction that fits a set of labeled examples. |
| Outcome: | The proposed model achieves 65.7% of human performance while the original model only reaches 9.8% of human performances. |
Machine Reading of Historical Events (2020.acl-main)
Copied to clipboard
| Challenge: | Using a short text description of an event, we can extract relevant sentences from Wikipedia and apply a combination of task-specific and general-purpose feature embeddings for the classification. |
| Approach: | They propose to use Wikipedia sentences to extract relevant sentences and apply feature embeddings to the task. |
| Outcome: | The proposed model outperforms the historical event ordering task and the event focus time task in the literature. |
A Chain-of-Thought Is as Strong as Its Weakest Link: A Benchmark for Verifiers of Reasoning Chains (2024.acl-long)
Copied to clipboard
Alon Jacovi, Yonatan Bitton, Bernd Bohnet, Jonathan Herzig, Or Honovich, Michael Tseng, Michael Collins, Roee Aharoni, Mor Geva
| Challenge: | Recent literature discusses automatic methods to evaluate reasoning to improve their correctness, but no fine-grained step-level datasets are available to enable thorough evaluation of such verification methods. |
| Approach: | They propose to benchmark automatic verifiers of complex Chain-of-Thought reasoning in open-domain question-answering settings using a dataset that includes comprehensive labels for relevance, attribution to evidence passages, and logical correctness of each reasoning step. |
| Outcome: | The proposed dataset shows that verifiers struggle at verifying reasoning chains, particularly verifying logical correctness and detecting contradictions. |
Keep Guessing? When Considering Inference Scaling, Mind the Baselines (2025.findings-naacl)
Copied to clipboard
| Challenge: | Experiments spanning mathematical reasoning and factual knowledge reveal that repeated sampling improves coverage in large language models. |
| Approach: | They define a baseline that enumerates answers according to their prevalence in the training set and then scale it to measure coverage. |
| Outcome: | The proposed model outperforms repeated model sampling for some LLMs while the coverage for others is on par with that of a mixture strategy that obtains k answers by using only 10 model samples and guessing the remaining k-10 attempts via enumeration. |
TRUE: Re-evaluating Factual Consistency Evaluation (2022.naacl-main)
Copied to clipboard
Or Honovich, Roee Aharoni, Jonathan Herzig, Hagai Taitelbaum, Doron Kukliansy, Vered Cohen, Thomas Scialom, Idan Szpektor, Avinatan Hassidim, Yossi Matias
| Challenge: | Grounded text generation systems often generate factual inconsistencies, hindering their real-world applicability. |
| Approach: | They propose a method to assess factual consistency metrics on standardized texts . they recommend NLI and question generation-and-answering-based methods as starting points . |
| Outcome: | The proposed method is more actionable and interpretable than previous methods. |