Related papers: GRACE: Generative Representation Learning via Cont…

Existing large language model (LLM)-based embeddings typically adopt an encoder-only paradigm, treating LLMs as static feature extractors and overlooking their core generative strengths. We introduce GIRCSE (Generative Iterative Refinement…

Inverse Reinforcement Learning aims to recover reward models from expert demonstrations, but traditional methods yield black-box models that are difficult to interpret and debug. In this work, we introduce GRACE (Generating Rewards As…

Large Language Models (LLMs) have demonstrated remarkable capabilities in natural language understanding and generation. However, their immense number of parameters and complex transformer-based architectures result in significant resource…

Retrieval-Augmented Generation (RAG) integrates external knowledge to enhance Large Language Models (LLMs), yet systems remain susceptible to two critical flaws: providing correct answers without explicit grounded evidence and producing…

Despite the recent development in the topic of explainable AI/ML for image and text data, the majority of current solutions are not suitable to explain the prediction of neural network models when the datasets are tabular and their features…

In the context of multi-step reasoning, e.g., with chain-of-thought, language models (LMs) can easily assign a high likelihood to incorrect steps. As a result, decoding strategies that optimize for solution likelihood often yield incorrect…

Assessing the reliability of Large Language Models (LLMs) by confidence elicitation is a prominent approach to AI safety in high-stakes applications, such as healthcare and finance. Existing methods either require expensive computational…

Compiler pass selection and phase ordering present a significant challenge in achieving optimal program performance, particularly for objectives like code size reduction. Standard compiler heuristics offer general applicability but often…

GRPO is a standard approach to endowing pretrained LLMs with reasoning capabilities. It estimates the advantage of an outcome from a group of $K$ outcomes, and promotes those with positive advantages inside a trust region. Since GRPO…

Large Language Models (LLMs) adapted via contrastive learning excel in general representation learning but struggle in vertical domains like chemistry and law, primarily due to a lack of domain-specific knowledge. This work identifies a…

LLMs excel in localized code completion but struggle with repository-level tasks due to limited context windows and complex semantic and structural dependencies across codebases. While Retrieval-Augmented Generation (RAG) mitigates context…

Unsupervised representation learning has recently received lots of interest due to its powerful generalizability through effectively leveraging large-scale unlabeled data. There are two prevalent approaches for this, contrastive learning…

In reinforcement learning (RL), it is easier to solve a task if given a good representation. While deep RL should automatically acquire such good representations, prior work often finds that learning representations in an end-to-end fashion…

Recently, large language models (LLMs) have emerged as a groundbreaking technology and their unparalleled text generation capabilities have sparked interest in their application to the fundamental sentence representation learning task.…

The rapid evolution of large language models (LLMs) represents a substantial leap forward in natural language understanding and generation. However, alongside these advancements come significant challenges related to the accountability and…

Recently, using large language models (LLMs) for data augmentation has led to considerable improvements in unsupervised sentence embedding models. However, existing methods encounter two primary challenges: limited data diversity and high…

Large language models (LLMs) achieve strong performance on plain text tasks but underperform on structured data like tables and databases. Potential challenges arise from their underexposure during pre-training and rigid text-to-structure…

Techniques that learn improved representations via offline data or self-supervised objectives have shown impressive results in traditional reinforcement learning (RL). Nevertheless, it is unclear how improved representation learning can…

Large language models (LLMs) with explicit reasoning capabilities excel at mathematical reasoning yet still commit process errors, such as incorrect calculations, brittle logic, and superficially plausible but invalid steps. In this paper,…

Retrieval-Augmented Generation (RAG) delivers substantial value in knowledge-intensive applications. However, its generated responses often lack transparent reasoning paths that trace back to source evidence from retrieved documents. This…