相关论文: Improving Bot Response Contradiction Detection via…

Existing NLP work commonly treats contradictions as errors to be resolved by choosing which statements to accept or discard. Yet a key aspect of human reasoning in social interactions and professional domains is the ability to hypothesize…

Social media bot detection has always been an arms race between advancements in machine learning bot detectors and adversarial bot strategies to evade detection. In this work, we bring the arms race to the next level by investigating the…

While recent years have witnessed the emergence of various explainable methods in machine learning, to what degree the explanations really represent the reasoning process behind the model prediction -- namely, the faithfulness of…

Interactive spoken dialog provides many new challenges for spoken language systems. One of the most critical is the prevalence of speech repairs. This paper presents an algorithm that detects and corrects speech repairs based on finding the…

Conversation systems accommodate diverse users with unique personalities and distinct writing styles. Within the domain of multi-turn dialogue modeling, this work studies the impact of varied utterance lengths on the quality of subsequent…

In a plethora of recent work, large language models (LLMs) demonstrated impressive reasoning ability, but many proposed downstream reasoning tasks only focus on final answers. Two fundamental questions persist: 1) how consistent is the…

Reward models have become a staple in modern NLP, serving as not only a scalable text evaluator, but also an indispensable component in many alignment recipes and inference-time algorithms. However, while recent reward models increase…

In this work, we propose a novel perspective to the problem of patch correctness assessment: a correct patch implements changes that "answer" to a problem posed by buggy behaviour. Concretely, we turn the patch correctness assessment into a…

Learning high quality sentence embeddings from dialogues has drawn increasing attentions as it is essential to solve a variety of dialogue-oriented tasks with low annotation cost. Annotating and gathering utterance relationships in…

When the world changes, so does the text that humans write about it. How do we build language models that can be easily updated to reflect these changes? One popular approach is retrieval-augmented generation, in which new documents are…

Large language models (LLMs) present significant risks when used to generate non-factual content and spread disinformation at scale. Detecting such LLM-generated content is crucial, yet current detectors often struggle to generalize in…

Large Language Models (LLMs) such as ChatGPT can infer personal attributes from seemingly innocuous text, raising privacy risks beyond memorized data leakage. While prior work has demonstrated these risks, little is known about how users…

This paper explores the use of text data augmentation techniques to enhance conflict and duplicate detection in software engineering tasks through sentence pair classification. The study adapts generic augmentation techniques such as…

Neural models for response generation produce responses that are semantically plausible but not necessarily factually consistent with facts describing the speaker's persona. These models are trained with fully supervised learning where the…

Misunderstandings arise not only in interpersonal communication but also between humans and Large Language Models (LLMs). Such discrepancies can make LLMs interpret seemingly unambiguous questions in unexpected ways, yielding incorrect…

In dialogues, an utterance is a chain of consecutive sentences produced by one speaker which ranges from a short sentence to a thousand-word post. When studying dialogues at the utterance level, it is not uncommon that an utterance would…

Automated Program Repair (APR) aims to automatically generate patches for rectifying software bugs. Recent strides in Large Language Models (LLM), such as ChatGPT, have yielded encouraging outcomes in APR, especially within the…

Ensuring that code accurately reflects the algorithms and methods described in research papers is critical for maintaining credibility and fostering trust in AI research. This paper presents a novel system designed to verify code…

A good open-domain chatbot should avoid presenting contradictory responses about facts or opinions in a conversational session, known as its consistency capacity. However, evaluating the consistency capacity of a chatbot is still…

The ability to revise in response to feedback is critical to students' writing success. In the case of argument writing in specific, identifying whether an argument revision (AR) is successful or not is a complex problem because AR quality…