Related papers: Assessing Human Editing Effort on LLM-Generated Te…
Controlling the attribute intensity of text generation is crucial across scenarios (e.g., writing conciseness, chatting emotion, and explanation clarity). The remarkable capabilities of large language models (LLMs) have revolutionized text…
Commit messages are natural language descriptions of code changes, which are important for program understanding and maintenance. However, writing commit messages manually is time-consuming and laborious, especially when the code is updated…
Reliable evaluation of large language model (LLM)-generated summaries remains an open challenge, particularly across heterogeneous domains and document lengths. We conduct a comprehensive meta-evaluation of 14 automatic summarization…
This work investigates context compression for Large Language Models (LLMs) using learned compression tokens to reduce the memory and computational demands of processing long sequences. We demonstrate that pre-trained LLMs can be fine-tuned…
Commit messages are crucial for documenting software changes, aiding in program comprehension and maintenance. However, creating effective commit messages is often overlooked by developers due to time constraints and varying levels of…
Natural language generation (NLG) spans a broad range of tasks, each of which serves for specific objectives and desires different properties of generated text. The complexity makes automatic evaluation of NLG particularly challenging.…
Large Language Models (LLMs) have significantly advanced natural language processing, demonstrating strong capabilities in tasks such as text generation, summarization, and reasoning. Recently, their potential for automating precise text…
Knowledge editing methods (KEs) are a cost-effective way to update the factual content of large language models (LLMs), but they pose a dual-use risk. While KEs are beneficial for updating outdated or incorrect information, they can be…
The task of generating natural language descriptions from images has received a lot of attention in recent years. Consequently, it is becoming increasingly important to evaluate such image captioning approaches in an automatic manner. In…
The emergence of Mixture of Experts (MoE) LLMs has significantly advanced the development of language models. Compared to traditional LLMs, MoE LLMs outperform traditional LLMs by achieving higher performance with considerably fewer…
Patients frequently seek information during their medical journeys, but the rising volume of digital patient messages has strained healthcare systems. Large language models (LLMs) offer promise in generating draft responses for clinicians,…
Evaluating personalized text generated by large language models (LLMs) is challenging, as only the LLM user, i.e., prompt author, can reliably assess the output, but re-engaging the same individuals across studies is infeasible. This paper…
Precisely controlling the length of generated text is a common requirement in real-world applications. However, despite significant advancements in following human instructions, Large Language Models (LLMs) still struggle with this task. In…
As research in large language models (LLMs) continues to accelerate, LLM-based evaluation has emerged as a scalable and cost-effective alternative to human evaluations for comparing the ever increasing list of models. This paper…
Despite the growing adoption of large language models (LLMs) in academic workflows, their capabilities remain limited in supporting high-quality scientific writing. Most existing systems are designed for general-purpose scientific text…
Large Language Models (LLMs) have demonstrated impressive capabilities in understanding and generating codes. Due to these capabilities, many recent methods are proposed to automatically refine the codes with LLMs. However, we should…
The breakthrough performance of large language models (LLMs) comes with major computational footprints and high deployment costs. In this paper, we progress towards resolving this problem by proposing a novel structured compression approach…
Post-editing has proven effective in improving the quality of text generated by large language models (LLMs) such as GPT-3.5 or GPT-4, particularly when direct updating of their parameters to enhance text quality is infeasible or expensive.…
Recently, program synthesis driven by large language models (LLMs) has become increasingly popular. However, program synthesis for machine learning (ML) tasks still poses significant challenges. This paper explores a novel form of program…
In this paper, we propose a rotation-constrained compensation method to address the errors introduced by structured pruning of large language models (LLMs). LLMs are trained on massive datasets and accumulate rich semantic knowledge in…