arXiv subjects

Hyeri Lee

Publications and source records attributed to Hyeri Lee.

5 recordsLinked to original sources

arXiv2025

Conflict-Aware Soft Prompting for Retrieval-Augmented Generation

Retrieval-augmented generation (RAG) enhances the capabilities of large language models (LLMs) by incorporating external knowledge into their input prompts. However, when the retrieved context contradicts the LLM's parametric knowledge, it often fails to resolve the conflict between incorrect external context and correct parametric knowledge, known as context-memory conflict. To tackle this problem, we introduce Conflict-Aware REtrieval-Augmented Generation (CARE), consisting of a context assessor and a base LLM. The context assessor encodes compact memory token embeddings from raw context tokens. Through grounded/adversarial soft prompting, the context assessor is trained to discern unreliable context and capture a guidance signal that directs reasoning toward the more reliable knowledge source. Extensive experiments show that CARE effectively mitigates context-memory conflicts, leading to an average performance gain of 5.0\% on QA and fact-checking benchmarks, establishing a promising direction for trustworthy and adaptive RAG systems.

cs.CL↗

arXiv2025

Typed-RAG: Type-Aware Decomposition of Non-Factoid Questions for Retrieval-Augmented Generation

Addressing non-factoid question answering (NFQA) remains challenging due to its open-ended nature, diverse user intents, and need for multi-aspect reasoning. These characteristics often reveal the limitations of conventional retrieval-augmented generation (RAG) approaches. To overcome these challenges, we propose Typed-RAG, a framework for type-aware decomposition of non-factoid questions (NFQs) within the RAG paradigm. Specifically, Typed-RAG first classifies an NFQ into a predefined type (e.g., Debate, Experience, Comparison). It then decomposes the question into focused sub-queries, each focusing on a single aspect. This decomposition enhances both retrieval relevance and answer quality. By combining the results of these sub-queries, Typed-RAG produces more informative and contextually aligned responses. Additionally, we construct Wiki-NFQA, a benchmark dataset for NFQA covering a wide range of NFQ types. Experiments show that Typed-RAG consistently outperforms existing QA approaches based on LLMs or RAG methods, validating the effectiveness of type-aware decomposition for improving both retrieval quality and answer generation in NFQA. Our code and dataset are available on https://github.com/TeamNLP/Typed-RAG.

cs.CL↗

arXiv2024

Multi-Granularity Guided Fusion-in-Decoder

In Open-domain Question Answering (ODQA), it is essential to discern relevant contexts as evidence and avoid spurious ones among retrieved results. The model architecture that uses concatenated multiple contexts in the decoding phase, i.e., Fusion-in-Decoder, demonstrates promising performance but generates incorrect outputs from seemingly plausible contexts. To address this problem, we propose the Multi-Granularity guided Fusion-in-Decoder (MGFiD), discerning evidence across multiple levels of granularity. Based on multi-task learning, MGFiD harmonizes passage re-ranking with sentence classification. It aggregates evident sentences into an anchor vector that instructs the decoder. Additionally, it improves decoding efficiency by reusing the results of passage re-ranking for passage pruning. Through our experiments, MGFiD outperforms existing models on the Natural Questions (NQ) and TriviaQA (TQA) datasets, highlighting the benefits of its multi-granularity solution.

cs.CL↗

arXiv2015

Cold electron beams from cryo-cooled, alkali antimonide photocathodes

In this letter we report on the generation of cold electron beams using a Cs3Sb photocathode grown by co-deposition of Sb and Cs. By cooling the photocathode to 90 K we demonstrate a significant reduction in the mean transverse energy validating the long standing speculation that the lattice temperature contribution limits the mean transverse energy or thermal emittance near the photoemission threshold, opening new frontiers in generating ultra-bright beams. At 90 K, we achieve a record low thermal emittance of 0.2 $μ$m (rms) per mm of laser spot diameter from an ultrafast (sub-picosecond) photocathode with quantum efficiency greater than $7\times 10^{-5}$ using a visible laser wavelength of 690 nm.

physics.acc-ph↗

arXiv2013

Demonstration of Low Emittance in the Cornell Energy Recovery Linac Injector Prototype

We present a detailed study of the six-dimensional phase space of the electron beam produced by the Cornell Energy Recovery Linac Photoinjector, a high-brightness, high repetition rate (1.3 GHz) DC photoemission source designed to drive a hard x-ray energy recovery linac (ERL). A complete simulation model of the injector has been constructed, verified by measurement, and optimized. Both the horizontal and vertical 2D transverse phase spaces, as well as the time-resolved (sliced) horizontal phase space, were simulated and directly measured at the end of the injector for 19 pC and 77 pC bunches at roughly 8 MeV. These bunch charges were chosen because they correspond to 25 mA and 100 mA average current if operating at the full 1.3 GHz repetition rate. The resulting 90% normalized transverse emittances for 19 (77) pC/bunch were 0.23 +/- 0.02 (0.51 +/- 0.04) microns in the horizontal plane, and 0.14 +/- 0.01 (0.29 +/- 0.02) microns in the vertical plane, respectively. These emittances were measured with a corresponding bunch length of 2.1 +/- 0.1 (3.0 +/- 0.2) ps, respectively. In each case the rms momentum spread was determined to be on the order of 1e-3. Excellent overall agreement between measurement and simulation has been demonstrated. Using the emittances and bunch length measured at 19 pC/bunch, we estimate the electron beam quality in a 1.3 GHz, 5 GeV hard x-ray ERL to be at least a factor of 20 times better than that of existing storage rings when the rms energy spread of each device is considered. These results represent a milestone for the field of high-brightness, high-current photoinjectors.

physics.acc-ph↗