Related papers: FineRef: Fine-Grained Error Reflection and Correct…
Large language models (LLM) often hallucinate, and while adding citations is a common solution, it is frequently insufficient for accountability as users struggle to verify how a cited source supports a generated claim. Existing methods are…
Large Reasoning Models (LRMs) have recently shown impressive performance on complex reasoning tasks, often by engaging in self-reflective behaviors such as self-critique and backtracking. However, not all reflections are beneficial-many are…
Large language models (LLMs) have demonstrated impressive performance on several tasks and are increasingly deployed in real-world applications. However, especially in high-stakes settings, it becomes vital to know when the output of an LLM…
Recent years have witnessed growing interest in applying Large Reasoning Models (LRMs) to Machine Translation (MT). Existing approaches predominantly adopt a "think-first-then-translate" paradigm. Although explicit reasoning trajectories…
High-quality instruction-tuning data is crucial for developing Large Language Models (LLMs) that can effectively navigate real-world tasks and follow human instructions. While synthetic data generation offers a scalable approach for…
Language models (LMs) often exhibit undesirable text generation behaviors, including generating false, toxic, or irrelevant outputs. Reinforcement learning from human feedback (RLHF) - where human preference judgments on LM outputs are…
As language models (LMs) demonstrate their capabilities in various fields, their application to tasks requiring multi-round interactions has become increasingly popular. These tasks usually have complex dynamics, so supervised fine-tuning…
The constitutional framework of alignment aims to align large language models (LLMs) with value-laden principles written in natural language (such as to avoid using biased language). Prior work has focused on parameter fine-tuning…
Large Language Models (LLMs) excel in data synthesis but can be inaccurate in domain-specific tasks, which retrieval-augmented generation (RAG) systems address by leveraging user-provided data. However, RAGs require optimization in both…
Trustworthy language models should provide both correct and verifiable answers. However, citations generated directly by standalone LLMs are often unreliable. As a result, current systems insert citations by querying an external retriever…
While hallucinations of large language models could been alleviated through retrieval-augmented generation and citation generation, how the model utilizes internal knowledge is still opaque, and the trustworthiness of its generated answers…
Large Language Models (LLMs) often generate overly cautious and vague responses on sensitive topics, sacrificing helpfulness for safety. Existing evaluation frameworks lack systematic methods to identify and address specific weaknesses in…
Recent proprietary large language models (LLMs), such as GPT-4, have achieved a milestone in tackling diverse challenges in the biomedical domain, ranging from multiple-choice questions to long-form generations. To address challenges that…
Recently, large language models (LLMs) enhanced by self-reflection have achieved promising performance on machine translation. The key idea is guiding LLMs to generate translation with human-like feedback. However, existing self-reflection…
Current reasoning paradigms for LLMs include chain-of-thought, ReAct, and post-hoc self-critique. These paradigms rely on two assumptions that fail on long-horizon, multi-stage tasks. As a result, errors accumulate silently across reasoning…
Automatic prompt engineering aims to enhance the generation quality of large language models (LLMs). Recent works utilize feedbacks generated from erroneous cases to guide the prompt optimization. During inference, they may further retrieve…
Retrieval-augmented generation (RAG) frameworks enable large language models (LLMs) to retrieve relevant information from a knowledge base and incorporate it into the context for generating responses. This mitigates hallucinations and…
When completing knowledge-intensive tasks, humans sometimes need an answer and a corresponding reference passage for auxiliary reading. Previous methods required obtaining pre-segmented article chunks through additional retrieval models.…
Addressing the critical need for robust safety in Large Language Models (LLMs), particularly against adversarial attacks and in-distribution errors, we introduce Reinforcement Learning with Backtracking Feedback (RLBF). This framework…
To enhance Large Language Models' (LLMs) reliability, calibration is essential -- the model's assessed confidence scores should align with the actual likelihood of its responses being correct. However, current confidence elicitation methods…