Related papers: PPL-MCTS: Constrained Textual Generation Through D…

Recent work on controlled text generation has either required attribute-based fine-tuning of the base language model (LM), or has restricted the parameterization of the attribute discriminator to be compatible with the base autoregressive…

Monte Carlo Tree Search (MCTS) has emerged as a powerful tool for decision-making in robotics, enabling efficient exploration of large search spaces. However, traditional MCTS methods struggle in environments characterized by high…

Recent work has framed constrained text generation with autoregressive language models as a probabilistic inference problem. Among these, Zhao et al. (2024) introduced a promising approach based on twisted Sequential Monte Carlo, which…

Recent studies have applied large language models (LLMs) to machine translation quality estimation (MTQE) by prompting models to assign numeric scores. Nonetheless, these direct scoring methods tend to show low segment-level correlation…

The growing scale of Large Language Models (LLMs) has exacerbated inference latency and computational costs. Speculative decoding methods, which aim to mitigate these issues, often face inefficiencies in the construction of token trees and…

It has been a common approach to pre-train a language model on a large corpus and fine-tune it on task-specific data. In practice, we observe that fine-tuning a pre-trained model on a small dataset may lead to over- and/or under-estimation…

Monte Carlo Tree Search (MCTS) has recently emerged as a powerful technique for enhancing the reasoning capabilities of LLMs. Techniques such as SFT or DPO have enabled LLMs to distill high-quality behaviors from MCTS, improving their…

Large language models (LLMs) have demonstrated remarkable proficiency in machine translation (MT), even without specific training on the languages in question. However, translating rare words in low-resource or domain-specific contexts…

Large Language Models (LLMs) have shown remarkable capabilities in code generation tasks, yet they face significant limitations in handling complex, long-context programming challenges and demonstrating complex compositional reasoning…

Pre-trained Transformer language models (LM) have become go-to text representation encoders. Prior research fine-tunes deep LMs to encode text sequences such as sentences and passages into single dense vector representations for efficient…

The need for interpretability in deep learning has driven interest in counterfactual explanations, which identify minimal changes to an instance that change a model's prediction. Current counterfactual (CF) generation methods require…

Large language models (LLMs) have shown strong knowledge reserves and task-solving capabilities, but still face the challenge of severe hallucination, hindering their practical application. Though scientific theories and rules can…

Existing Large Language Models (LLMs) generate text through unidirectional autoregressive decoding methods to respond to various user queries. These methods tend to consider token selection in a simple sequential manner, making it easy to…

Monte Carlo Tree Search (MCTS) is a powerful approach to designing game-playing bots or solving sequential decision problems. The method relies on intelligent tree search that balances exploration and exploitation. MCTS performs random…

Ensuring both syntactic and semantic correctness in Large Language Model (LLM) outputs remains a significant challenge, despite being critical for real-world deployment. In this paper, we introduce $\texttt{SEM-CTRL}$, a unified approach…

Recent advances in neural-based generative modeling have reignited the hopes of having computer systems capable of conversing with humans and able to understand natural language. The employment of deep neural architectures has been largely…

We have seen significant improvements in machine translation due to the usage of deep learning. While the improvements in translation quality are impressive, the encoder-decoder architecture enables many more possibilities. In this paper,…

Data-driven generative models excel in language and vision, but diffusion models often fail in constrained planning and design tasks, exhibiting severe constraint violations in engineering inverse design, molecular generation, multi-robot…

Generic generation and manipulation of text is challenging and has limited success compared to recent deep generative modeling in visual domain. This paper aims at generating plausible natural language sentences, whose attributes are…

Pretrained Transformer-based language models (LMs) display remarkable natural language generation capabilities. With their immense potential, controlling text generation of such LMs is getting attention. While there are studies that seek to…