Christopher E. Potts · page 2
Papers
- Not a Simple Yes or No: Uncertainty in Indirect Answers (2009 · 23 citations)
Answers to yes/no questions are often indirect. Sometimes the reply only makes "yes" or "no" more or less likely without settling the question. Earlier plan-based, purely logical models, such as Green and Carberry's, cannot weigh such uncertain or conflicting evidence. The authors study these indirect question–answer… - Pragmatic Issue-Sensitive Image Captioning (2020 · 21 citations)
The paper argues that a good caption must be both true and relevant to what the reader currently cares about. - Anchored Preference Optimization and Contrastive Revisions: Addressing Underspecification in Alignment (2025 · 20 citations)
The authors argue that preference-based alignment of LLMs is underspecified in two ways. First, the winning and losing responses in a preference pair often differ in many irrelevant aspects, which blurs what the model should learn. Second, standard contrastive objectives do not consider whether the target model is… - CAW-coref: Conjunction-Aware Word-level Coreference Resolution (2023 · 17 citations)
Coreference resolution groups text mentions that point to the same entity. The strongest current systems call large language models many times per document, which is too costly for large-scale information extraction. Word-level coreference (WL-coref) is much cheaper. A single pass of roberta-large produces word… - Lexical Semantics with Large Language Models: A Case Study of English “break” (2023 · 17 citations)
The paper asks whether large language models can serve as research instruments for lexical semantics, using the English verb break as a test case. - Causal Interventions Reveal Shared Structure Across English Filler–Gap Constructions (2025 · 13 citations)
The paper asks whether a language model uses one shared mechanism for several English filler–gap constructions (embedded wh-questions, matrix wh-questions, relative clauses, clefts, pseudo-clefts, topicalization). - MSCAW-coref: Multilingual, Singleton and Conjunction-Aware Word-Level Coreference Resolution (2024 · 8 citations)
Strong multilingual coreference systems usually enumerate candidate spans and then connect them, so their cost grows as O(n^4) in document length. - Color Overmodification Emerges from Data-Driven Learning and Pragmatic Reasoning (2022 · 1 citation)
Human speakers often name an object's color even when its shape alone would single it out. This redundancy is common for objects that come in many colors. It drops when the color is the expected one, and it is thought to depend on how visually salient color is. Earlier accounts, including RSA-based ones, start from a…
This page in Markdown → https://md.research.elamur.ai/free/en/authors/christopher-e-potts/page/2/