Related papers: A Dialectic Pipeline for Improving LLM Robustness

This article presents a pipeline for automated fact-checking leveraging publicly available Language Models and data. The objective is to assess the accuracy of textual claims using evidence from a ground-truth evidence corpus. The pipeline…

Large Language Models (LLMs) have demonstrated exceptional capabilities, yet selecting the most reliable response from multiple LLMs remains a challenge, particularly in resource-constrained settings. Existing approaches often depend on…

As large language models (LLMs) become increasingly powerful, traditional evaluation metrics tend to saturate, making it challenging to distinguish between models. We propose a general method to transform existing LLM evaluations into a…

To mitigate hallucinations in large language models (LLMs), we propose a framework that focuses on errors induced by prompts. Our method extends a chain-style knowledge distillation approach by incorporating a programmable module that…

Many studies have proposed methods for optimizing the dialogue performance of an entire pipeline task-oriented dialogue system by jointly training modules in the system using reinforcement learning. However, these methods are limited in…

Certain strong LLMs have shown promise for zero-shot formal planning by generating planning languages like PDDL. Yet, the performance of most open-source models under 50B parameters has been reported to be close to zero due to the…

Large Language Models (LLMs) still struggle with complex logical reasoning. While previous works achieve remarkable improvements, their performance is highly dependent on the correctness of translating natural language (NL) problems into a…

Effective training of language models (LMs) for mathematical reasoning tasks demands high-quality supervised fine-tuning data. Besides obtaining annotations from human experts, a common alternative is sampling from larger and more powerful…

Despite the increasing effectiveness of language models, their reasoning capabilities remain underdeveloped. In particular, causal reasoning through counterfactual question answering is lacking. This work aims to bridge this gap. We first…

As sharing images in an instant message is a crucial factor, there has been active research on learning an image-text multi-modal dialogue models. However, training a well-generalized multi-modal dialogue model remains challenging due to…

While conditional language models have greatly improved in their ability to output high-quality natural language, many NLP applications benefit from being able to generate a diverse set of candidate sequences. Diverse decoding strategies…

Recent methods have demonstrated that Large Language Models (LLMs) can solve reasoning tasks better when they are encouraged to solve subtasks of the main task first. In this paper we devise a similar strategy that breaks down reasoning…

The sequential recommendation problem has attracted considerable research attention in the past few years, leading to the rise of numerous recommendation models. In this work, we explore how Large Language Models (LLMs), which are nowadays…

Large language models (LLMs) offer significant potential to accelerate systematic literature reviews (SLRs), yet current approaches often rely on brittle, manually crafted prompts that compromise reliability and reproducibility. This…

This work presents an ontology-integrated large language model (LLM) framework for chemical engineering that unites structured domain knowledge with generative reasoning. The proposed pipeline aligns model training and inference with the…

Cross-domain analogical reasoning is a core creative ability that can be challenging for humans. Recent work has shown some proofs-of concept of Large language Models' (LLMs) ability to generate cross-domain analogies. However, the…

The rapid advancement of large language models (LLMs) has significantly impacted various domains, including healthcare and biomedicine. However, the phenomenon of hallucination, where LLMs generate outputs that deviate from factual accuracy…

With the rise of long-context language models (LMs) capable of processing tens of thousands of tokens in a single context window, do multi-stage retrieval-augmented generation (RAG) pipelines still offer measurable benefits over simpler,…

Recent works have demonstrated success in controlling sentence attributes ($e.g.$, sentiment) and structure ($e.g.$, syntactic structure) based on the diffusion language model. A key component that drives theimpressive performance for…

We study the potential of using large language models (LLMs) as an interactive optimizer for solving maximization problems in a text space using natural language and numerical feedback. Inspired by the classical optimization literature, we…