Search Results for author:
Found 16 papers, 7 papers with code
From Models to Microtheories: Distilling a Model's Topical Knowledge for Grounded Question Answering
We show that, when added to a general corpus (e. g., Wikipedia), microtheories can supply critical, topical information not necessarily present in the corpus, improving both a model's ability to ground its answers to verifiable knowledge (i. e., show how answers are systematically entailed by documents in the corpus, fully grounding up to +8% more answers), and the accuracy of those grounded answers (up to +8% absolute).
Core: Robust Factual Precision with Informative Sub-Claim Identification
Hallucinations pose a challenge to the application of large language models (LLMs) thereby motivating the development of metrics to evaluate factual precision.
Learning to Reason via Program Generation, Emulation, and Search
CoGEX works by (1) training LMs to generate pseudo-programs, (2) teaching them to emulate their generated program's execution, including those leaf functions, allowing the LM's knowledge to fill in the execution gaps; and (3) using them to search over many programs to find an optimal one.
SELF-[IN]CORRECT: LLMs Struggle with Discriminating Self-Generated Responses
For this to be true, LLMs would need to be better at discriminating among previously-generated alternatives, than generating initial responses.
TV-TREES: Multimodal Entailment Trees for Neuro-Symbolic Video Reasoning
It is challenging for models to understand complex, multimodal content such as television clips, and this is in part because video-language models often rely on single-modality reasoning and lack interpretability.
Enhancing Systematic Decompositional Natural Language Inference Using Informal Logic
Recent language models enable new opportunities for structured reasoning with text, such as the construction of intuitive, proof-like textual entailment trees without relying on brittle formal logic.
Reframing Tax Law Entailment as Analogical Reasoning
We re-frame statutory reasoning as an analogy task, where each instance of the analogy task involves a combination of two instances of statutory reasoning.
"According to ...": Prompting Language Models Improves Quoting from Pre-Training Data
Large Language Models (LLMs) may hallucinate and generate fake information, despite pre-training on factual data.
Ontologically Faithful Generation of Non-Player Character Dialogues
We introduce a language generation task grounded in a popular video game environment.
Defending Against Disinformation Attacks in Open-Domain Question Answering
Recent work in open-domain question answering (ODQA) has shown that adversarial poisoning of the search collection can cause large drops in accuracy for production systems.
NELLIE: A Neuro-Symbolic Inference Engine for Grounded, Compositional, and Explainable Reasoning
Our goal is a modern approach to answering questions via systematic reasoning where answers are supported by human interpretable proof trees grounded in an NL corpus of authoritative facts.
One-Shot Learning from a Demonstration with Hierarchical Latent Language
Humans have the capability, aided by the expressive compositionality of their language, to learn quickly by demonstration.
InFillmore: Frame-Guided Language Generation with Bidirectional Context
We propose a structured extension to bidirectional-context conditional language generation, or "infilling," inspired by Frame Semantic theory (Fillmore, 1976).
COD3S: Diverse Generation with Discrete Semantic Signatures
We present COD3S, a novel method for generating semantically diverse sentences using neural sequence-to-sequence (seq2seq) models.
Probing Neural Language Models for Human Tacit Assumptions
Our prompts are based on human responses in a psychological study of conceptual associations.
An End-to-end Neural Natural Language Interface for Databases
The ability to extract insights from new data sets is critical for decision making.
