Search Results for author:
Found 32 papers, 21 papers with code
Think about it! Improving defeasible reasoning by first modeling the question scenario.
Defeasible reasoning is the mode of reasoning where conclusions can be overturned by taking into account new evidence.
Synatra: Turning Indirect Knowledge into Direct Demonstrations for Digital Agents at Scale
LLMs can now act as autonomous agents that interact with digital environments and complete specific objectives (e. g., arranging an online meeting).
In-Context Principle Learning from Mistakes
We evaluate LEAP on a wide range of benchmarks, including multi-hop question answering (Hotpot QA), textual QA (DROP), Big-Bench Hard reasoning, and math problems (GSM8K and MATH); in all these benchmarks, LEAP improves the strongest available LLMs such as GPT-3. 5-turbo, GPT-4, GPT-4 turbo and Claude-2. 1.
Self-Imagine: Effective Unimodal Reasoning with Multimodal Models using Self-Imagination
The potential of Vision-Language Models (VLMs) often remains underutilized in handling complex text-based problems, particularly when these problems could benefit from visual representation.
Program-Aided Reasoners (better) Know What They Know
Our analysis uncovers that prompting styles that produce lesser diversity in generations also have more calibrated results, and thus we also experiment with inducing lower generation diversity using temperature scaling and find that for certain temperatures, PAL is not only more accurate but is also more calibrated than COT.
AutoMix: Automatically Mixing Language Models
Large language models (LLMs) are now available from cloud API providers in various sizes and configurations.
How FaR Are Large Language Models From Agents with Theory-of-Mind?
We propose a new evaluation paradigm for large language models (LLMs): Thinking for Doing (T4D), which requires models to connect inferences about others' mental states to actions in social scenarios.
Let's Sample Step by Step: Adaptive-Consistency for Efficient Reasoning and Coding with LLMs
A popular approach for improving the correctness of output from large language models (LLMs) is Self-Consistency - poll the LLM multiple times and output the most frequent solution.
RL4F: Generating Natural Language Feedback with Reinforcement Learning for Repairing Model Outputs
Despite their unprecedented success, even the largest language models make mistakes.
Bridging the Gap: A Survey on Integrating (Human) Feedback for Natural Language Generation
Many recent advances in natural language generation have been fueled by training large language models on internet-scale data.
Self-Refine: Iterative Refinement with Self-Feedback
Motivated by how humans refine their written text, we introduce Self-Refine, an approach for improving initial outputs from LLMs through iterative feedback and refinement.
Learning Performance-Improving Code Edits
Next, we propose a broad range of adaptation strategies for code optimization; for prompting, these include retrieval-based few-shot prompting and chain-of-thought, and for finetuning, these include performance-conditioned generation and synthetic data augmentation based on self-play.
PAL: Program-aided Language Models
Much of this success can be attributed to prompting methods such as "chain-of-thought'', which employ LLMs for both understanding the problem description by decomposing it into steps, as well as solving each step of the problem.
Ranked #43 on
Math Word Problem Solving
on MATH
Language Models of Code are Few-Shot Commonsense Learners
In all these natural language tasks, we show that using our approach, a code generation LM (CODEX) outperforms natural-LMs that are fine-tuned on the target task (e. g., T5) and other strong LMs such as GPT-3 in the few-shot setting.
Text and Patterns: For Effective Chain of Thought, It Takes Two to Tango
Our empirical and qualitative analysis reveals that a symbiotic relationship between text and patterns explains the success of few-shot prompting: text helps extract commonsense from the question to help patterns, and patterns enforce task understanding and direct text generation.
FLOWGEN: Fast and slow graph generation
Machine learning systems typically apply the same model to both easy and tough cases.
GEMv2: Multilingual NLG Benchmarking in a Single Line of Code
This problem is especially pertinent in natural language generation which requires ever-improving suites of datasets, metrics, and human evaluation to make definitive claims.
Conditional set generation using Seq2seq models
Conditional set generation learns a mapping from an input sequence of tokens to a set.
Memory-assisted prompt editing to improve GPT-3 after deployment
Large LMs such as GPT-3 are powerful, but can commit mistakes that are obvious to humans.
Learning to Repair: Repairing model output errors after deployment using a dynamic memory of feedback
Our goal is for an LM to continue to improve after deployment, without retraining, using feedback from the user.
Interscript: A dataset for interactive learning of scripts through error feedback
We present a new dataset, Interscript, containing user feedback on a deployed model that generates complex everyday tasks.
Think about it! Improving defeasible reasoning by first modeling the question scenario
Defeasible reasoning is the mode of reasoning where conclusions can be overturned by taking into account new evidence.
Could you give me a hint? Generating inference graphs for defeasible reasoning
Defeasible reasoning is the mode of reasoning where conclusions can be overturned by taking into account new evidence.
Improving Neural Model Performance through Natural Language Feedback on Their Explanations
A class of explainable NLP models for reasoning tasks support their decisions by generating free-form or structured explanations, but what happens when these supporting structures contain errors?
CURIE: An Iterative Querying Approach for Reasoning About Situations
Recently, models have been shown to predict the effects of unexpected situations, e. g., would cloudy skies help or hinder plant growth?
The GEM Benchmark: Natural Language Generation, its Evaluation and Metrics
We introduce GEM, a living benchmark for natural language Generation (NLG), its Evaluation, and Metrics.
Ranked #1 on
Extreme Summarization
on GEM-XSum
Abstractive Text Summarization
Cross-Lingual Abstractive Summarization
+5
EIGEN: Event Influence GENeration using Pre-trained Language Models
Reasoning about events and tracking their influences is fundamental to understanding processes.
Neural Language Modeling for Contextualized Temporal Graph Generation
We address this challenge by using existing IE/NLP tools to automatically generate a large quantity (89, 000) of system-produced document-graph pairs, and propose a novel formulation of the contextualized graph generation problem as a sequence-to-sequence mapping task.
Politeness Transfer: A Tag and Generate Approach
This paper introduces a new task of politeness transfer which involves converting non-polite sentences to polite sentences while preserving the meaning.
Practical Comparable Data Collection for Low-Resource Languages via Images
We propose a method of curating high-quality comparable training data for low-resource languages with monolingual annotators.
Occurrence Statistics of Entities, Relations and Types on the Web
This is owing to the severe mismatch in the distributions of such entities on the web and in the relatively diminutive training data.
