Related papers: Towards Consistent Language Models Using Declarati…

LLMs are not generally able to adjust the length of their outputs based on strict length requirements, a capability that would improve their usefulness in applications that require adherence to diverse user and system requirements. We…

Deep learning models suffer from the problem of semantic discontinuity: small perturbations in the input space tend to cause semantic-level interference to the model output. We argue that the semantic discontinuity results from these…

Language enables humans to share knowledge, reason about the world, and pass on strategies for survival and innovation across generations. At the heart of this process is not just the ability to communicate but also the remarkable…

Recent studies have adopted pre-trained language models, such as CodeT5 and CodeGPT, for automated program generation tasks like code generation, repair, and translation. Numerous language model-based approaches have been proposed and…

In recent years, multimodal large language models (MLLMs) have achieved significant breakthroughs, enhancing understanding across text and vision. However, current MLLMs still face challenges in effectively integrating knowledge across…

Cross-lingual consistency should be considered to assess cross-lingual transferability, maintain the factuality of the model knowledge across languages, and preserve the parity of language model performance. We are thus interested in…

Current large language models (LLMs) generally show a significant performance gap in alignment between English and other languages. To bridge this gap, existing research typically leverages the model's responses in English as a reference to…

While large language models (LLMs) excel in mathematical and code reasoning, we observe they struggle with social reasoning tasks, exhibiting cognitive confusion, logical inconsistencies, and conflation between objective world states and…

Large pre-trained models have achieved great success in many natural language processing tasks. However, when they are applied in specific domains, these models suffer from domain shift and bring challenges in fine-tuning and online serving…

Large language models (LLMs) have demonstrated impressive capabilities in natural language processing. However, their internal mechanisms are still unclear and this lack of transparency poses unwanted risks for downstream applications.…

Early stages of system development involve outlining desired features such as functionality, availability, or usability. Specifications are derived from these features that concretize vague ideas presented in natural languages. The…

Understanding natural language requires common sense, one aspect of which is the ability to discern the plausibility of events. While distributional models -- most recently pre-trained, Transformer language models -- have demonstrated…

In an era dominated by data, the management and utilization of domain-specific language have emerged as critical challenges in various application domains, particularly those with industry-specific requirements. Our work is driven by the…

Large language models (LLMs), especially when instruction-tuned for chat, have become part of our daily lives, freeing people from the process of searching, extracting, and integrating information from multiple sources by offering a…

Efforts to apply transformer-based language models (TLMs) to the problem of reasoning in natural language have enjoyed ever-increasing success in recent years. The most fundamental task in this area to which nearly all others can be reduced…

The increasing use of Large Language Models (LLMs) as proxies for human participants in social science research presents a promising, yet methodologically risky, paradigm shift. While LLMs offer scalability and cost-efficiency, their…

While large language models (LLMs) have rapidly improved their performance on a broad number of tasks, they still often fall short on reasoning tasks. As LLMs become more integrated in diverse real-world tasks, advancing their reasoning…

Aligning large language models (LLMs) to human preferences is challenging in domains where preference data is unavailable. We address the problem of learning reward models for such target domains by leveraging feedback collected from…

Generating responses that are consistent with the dialogue context is one of the central challenges in building engaging conversational agents. We demonstrate that neural conversation models can be geared towards generating consistent…

Large Language Models (LLMs) have demonstrated impressive mathematical reasoning capabilities, yet their performance remains brittle to minor variations in problem description and prompting strategy. Furthermore, reasoning is vulnerable to…